© 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. 44837
    Prev
    Next
    INDEX
    Explanations

    geographic or administrative descriptor

    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
    鹇
    -2.72
    蹰
    -2.70
    ఙ
    -2.55
    呖
    -2.53
    轳
    -2.42
    莇
    -2.41
    屣
    -2.38
    憷
    -2.38
    神
    -2.31
    ケモン
    -2.30
    POSITIVE LOGITS
    );
    2.91
    ;
    2.91
    :
    2.77
    n
    2.34
    –
    2.27
    狆
    2.22
    š
    2.20
    X
    2.19
    «
    2.17
    緖
    2.16
    Activations Density 0.008%

    No Known Activations