© 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. 39777
    Prev
    Next
    INDEX
    Explanations

    Dundee, ADT, Jira, Madame

    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
    䊊
    -2.55
    genodigd
    -2.39
    苳
    -2.33
    Ruju
    -2.31
    部は
    -2.27
     钱
    -2.22
    多谢
    -2.22
    欸
    -2.20
    ikuti
    -2.17
     ());
    -2.17
    POSITIVE LOGITS
    D
    4.41
    H
    3.52
    ↵
    3.47
    ’
    3.34
    M
    3.13
    </strong>
    3.03
    Y
    2.95
    the
    2.92
    such
    2.92
    er
    2.89
    Activations Density 0.015%

    No Known Activations