© 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. 103212
    Prev
    Next
    INDEX
    Explanations

    LaTeX typesetting commands

    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
    urger
    -0.82
    getFloat
    -0.76
     сен
    -0.75
    Осно
    -0.73
    ższy
    -0.73
    JDK
    -0.73
    的值
    -0.73
    GeneratedValue
    -0.72
     Reservation
    -0.72
     peroxidase
    -0.71
    POSITIVE LOGITS
     italic
    0.82
     competitivo
    0.79
    maths
    0.77
     alimentaria
    0.76
     informativo
    0.75
    Gost
    0.75
    Creep
    0.75
     math
    0.74
    Glitch
    0.73
     slo
    0.73
    Activations Density 0.014%

    No Known Activations