© 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. 82459
    Prev
    Next
    INDEX
    Explanations

    law, court, cas

    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
    ゔ
    -0.79
    stray
    -0.77
     Большая
    -0.74
     כן
    -0.73
     STAY
    -0.73
    arev
    -0.71
    converters
    -0.71
    resol
    -0.70
    bait
    -0.69
     juzgar
    -0.69
    POSITIVE LOGITS
     специаль
    0.69
    ouv
    0.69
    fireEvent
    0.66
    anas
    0.64
    这个
    0.64
    堵
    0.63
     Paling
    0.63
    uje
    0.63
    飲み
    0.63
    合唱
    0.63
    Activations Density 0.044%

    No Known Activations