© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207268
    Prev
    Next
    INDEX
    Explanations

    brake bias

    np_acts-logits-general · gemini-2.5-flash-lite

    resource and market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    の良い
    0.46
     zapewnia
    0.44
     இசை
    0.44
    axter
    0.43
     질
    0.43
    czyk
    0.42
    doesn
    0.42
    ชาย
    0.42
     optimality
    0.41
    HISTORY
    0.41
    POSITIVE LOGITS
     in
    0.55
     from
    0.45
    িকালে
    0.43
     сегодня
    0.43
     Studio
    0.42
     yesterday
    0.42
    s
    0.42
    ();
    0.42
     hauptsächlich
    0.42
     welcome
    0.42
    Activations Density 0.001%

    No Known Activations