© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90706
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    玩笑
    -0.88
    Some
    -0.87
    rakech
    -0.86
    ければ
    -0.85
     нашей
    -0.85
    udo
    -0.84
    saia
    -0.84
     we
    -0.84
    该如何
    -0.83
    Another
    -0.83
    POSITIVE LOGITS
    ];
    1.14
    );
    1.07
     Messung
    1.03
    метра
    1.03
    .}(
    0.98
     visto
    0.96
    ﹤
    0.95
    😦
    0.95
    <[
    0.93
    稔
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.