© 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. 34601
    Prev
    Next
    INDEX
    Explanations

    */ summary para message

    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
     MemoryStream
    -0.85
     after
    -0.76
    ramientas
    -0.75
    imab
    -0.74
    ارش
    -0.74
    JMenu
    -0.73
    SqlSession
    -0.71
     Schaden
    -0.71
    nonumber
    -0.71
    getLatitude
    -0.70
    POSITIVE LOGITS
     fireworks
    0.85
     regulares
    0.84
    <blockquote>
    0.80
     Fireworks
    0.78
    ärsk
    0.78
     sén
    0.77
    まだ
    0.76
     Presidencia
    0.75
     glaring
    0.75
    dood
    0.73
    Activations Density 0.002%

    No Known Activations