© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102745
    Prev
    Next
    INDEX
    Explanations

    UUIDs and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    sequences of digits, particularly in technical contexts like file paths, IDs, codes, and numerical data.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     That
    -2.00
    嵛
    -1.96
     überprü
    -1.91
     veritable
    -1.87
    ໌
    -1.79
    that
    -1.77
     damal
    -1.76
     Так
    -1.73
     Unglück
    -1.73
     erzä
    -1.72
    POSITIVE LOGITS
    芎
    1.99
    鲆
    1.84
     itſelf
    1.77
    踯
    1.74
     you
    1.71
    \
    1.70
    🐴
    1.68
     terrestre
    1.67
    芣
    1.64
     zey
    1.63
    Activations Density 0.064%

    No Known Activations