Frizzle
An engraved night scene: a small vintage coach drives along a road through a row of glass panes, each a grid of points of light; on one pane a single point glows amber beside a brass dial that has just been turned.

Plainsight Systems · tech demo

Frizzle

Reach inside a language model, pin its neurons, and read what it says instead.

Gemma 3 1B runs entirely in your browser on WebGPU. Ask it something, ride through its 26 layers, turn a neuron up or down, and watch the answer change course.

Open Frizzle

What you can do

Ask the model something and it writes a reply. Pick any word of that reply and ride inside: you drive through the model’s 26 layers and watch its next word take shape, from nonsense to the answer.

Pin any of its neurons to a value of your choosing and ride again. The road forks at the layer where your pin changes the model’s mind, and Frizzle writes the new reply from there, from the same seed, beside the one the model first wrote. Every difference between the two is yours.

For a closer look, the Deck lays out all 6,912 neurons of every layer as cards you can flip through.

New here? Take the ride: one question, from Paris to Berlin.

What it needs

How it is built

The engine is C++ compiled to WebAssembly, running every step of the model on your GPU. The page is React and three.js. The model is Google’s Gemma 3 1B, instruction-tuned, in its 4-bit Q4_0 build. The source is on GitHub.