© 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. 85144
    Prev
    Next
    INDEX
    Explanations

    Kathryn names, propensity for certain actions

    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
    鐿
    -4.19
    ."
    -3.39
    𞤢
    -2.97
    蛩
    -2.80
    勠
    -2.80
    猡
    -2.80
    遄
    -2.69
    銪
    -2.67
    焿
    -2.67
    ﮨ
    -2.67
    POSITIVE LOGITS
    ↵↵
    3.16
    และ
    2.78
     But
    2.72
     miembros
    2.61
     “
    2.59
    身上的
    2.52
    莛
    2.48
    <i>
    2.45
    极为
    2.38
    已是
    2.36
    Activations Density 0.006%

    No Known Activations