© 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. 67002
    Prev
    Next
    INDEX
    Explanations

    code block comments

    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
    ichtete
    -2.28
    gunakan
    -1.99
    ⃤
    -1.92
    tedì
    -1.86
    ふう
    -1.77
    你可以
    -1.75
    anzug
    -1.73
    UAWEI
    -1.68
    　＊
    -1.68
    erenc
    -1.67
    POSITIVE LOGITS
    up
    2.64
    ate
    2.38
    .
    2.20
    have
    2.19
    ru
    2.16
    ran
    2.16
    are
    2.14
    ay
    2.13
    姐妹
    2.09
    ro
    2.08
    Activations Density 0.004%

    No Known Activations