© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 238
    Prev
    Next
    INDEX
    Explanations

    units and specifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ़
    0.42
    ತ್ಮ
    0.41
     خطاب
    0.40
    르
    0.40
    いただ
    0.39
    頊
    0.38
    ज़ा
    0.37
    ടക
    0.37
    ंझ
    0.37
    廰
    0.37
    POSITIVE LOGITS
     корпу
    0.47
    ными
    0.44
     Кор
    0.41
    ::*;
    0.40
    ствующих
    0.39
     of
    0.39
    nisse
    0.39
    ++;
    0.38
    /');
    0.38
    pected
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.