© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8693
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ></
    1.07
    ="<?
    1.04
    <?>
    1.00
    ="{{
    0.98
     Cardio
    0.94
    ="#"
    0.92
    ="'.$
    0.92
    =".
    0.90
    ObjectURL
    0.90
    "></
    0.87
    POSITIVE LOGITS
    GIT
    0.90
    桂
    0.89
     хто
    0.89
     wig
    0.87
     lavish
    0.85
     confront
    0.85
    шими
    0.85
     peeling
    0.84
     月
    0.84
    WY
    0.84
    Activations Density 0.005%

    No Known Activations