© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99503
    Prev
    Next
    INDEX
    Explanations

    reservoirs and lakes

    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
     mohou
    -1.62
    attente
    -1.55
    arrêt
    -1.55
    
    -1.55
    多彩
    -1.49
    Soporte
    -1.49
     ingenu
    -1.48
     trânsito
    -1.48
     кілька
    -1.47
     suporte
    -1.45
    POSITIVE LOGITS
    s
    1.51
     of
    1.50
     also
    1.49
    ">
    1.42
    );
    1.38
      
    1.37
    ,…
    1.36
     their
    1.34
    </h1>
    1.27
    ),
    1.25
    Activations Density 0.037%

    No Known Activations