© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85368
    Prev
    Next
    INDEX
    Explanations

    semicolons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -2.23
    In
    -2.03
     на
    -1.95
    '
    -1.92
    The
    -1.83
    <
    -1.73
     After
    -1.62
     "
    -1.59
    >
    -1.56
    Like
    -1.55
    POSITIVE LOGITS
    ⩥
    2.00
    rivial
    1.80
    蚡
    1.79
     墊
    1.70
    螣
    1.70
     unſ
    1.69
     ľudí
    1.66
    縢
    1.63
    ">)</
    1.61
    ୮
    1.61
    Activations Density 0.012%

    No Known Activations