© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 510
    Prev
    Next
    INDEX
    Explanations

    code block start with curly brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    )}(\
    0.80
    ortes
    0.73
    ](\
    0.69
    }]\
    0.69
    }^{-}\
    0.68
    やや
    0.68
    })(\
    0.68
    wicz
    0.67
     součástí
    0.66
    citet
    0.66
    POSITIVE LOGITS
     {
    2.76
     {//
    2.11
    {
    2.02
     {}
    1.63
    {//
    1.54
     {...
    1.52
    ｛
    1.51
     {};
    1.43
     {_
    1.40
     {(
    1.40
    Activations Density 0.055%

    No Known Activations