© 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. 34-GEMMASCOPE-RES-131K
    7. 608
    Prev
    Next
    INDEX
    Explanations

    saint names

    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_34/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
    ambung
    -0.84
    雪花
    -0.77
     Massage
    -0.77
    šanai
    -0.75
     TAMBÉM
    -0.73
    未能
    -0.73
     motivo
    -0.72
    verre
    -0.72
    ngua
    -0.71
     theoretical
    -0.71
    POSITIVE LOGITS
    arova
    0.90
     Méditerranée
    0.87
    ?”
    0.84
    hed
    0.84
    lified
    0.83
    hh
    0.83
    ');
    0.82
    oning
    0.82
    >());
    0.82
     constaté
    0.82
    Activations Density 0.018%

    No Known Activations