© 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. 162407
    Prev
    Next
    INDEX
    Explanations

    on behalf of

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

    only individual capabilities

    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
    Ⴀ
    0.59
     negation
    0.49
    所有的
    0.48
    ложение
    0.47
    ༸
    0.47
     ಉಪ
    0.47
    너
    0.47
    任
    0.46
     locker
    0.46
    每一
    0.46
    POSITIVE LOGITS
    ające
    0.49
    b
    0.47
    ang
    0.45
     Burnu
    0.44
    ap
    0.44
    endpoint
    0.43
    VOID
    0.43
    ut
    0.43
     تنگ
    0.42
    bv
    0.42
    Activations Density 0.001%

    No Known Activations