© 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. 67217
    Prev
    Next
    INDEX
    Explanations

    code in multiple languages

    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
     a
    0.67
    -
    0.66
    (
    0.64
    (-
    0.60
    -}
    0.59
    =
    0.59
    kker
    0.57
    de
    0.57
    ating
    0.57
    َف
    0.56
    POSITIVE LOGITS
    ע
    0.80
    ي
    0.73
    י
    0.71
    ი
    0.70
     Ну
    0.69
    도
    0.68
     ﺍ
    0.67
    트
    0.66
    ра
    0.65
    ה
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.