© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1048
    Prev
    Next
    INDEX
    Explanations

    news and official reports

    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
     angusti
    -0.89
     Gesetze
    -0.78
     eras
    -0.73
     magg
    -0.72
     needed
    -0.72
    ema
    -0.72
    нева
    -0.72
     утвер
    -0.71
    LJ
    -0.71
    TWO
    -0.71
    POSITIVE LOGITS
     scandalous
    0.86
     conflict
    0.86
     shepherds
    0.84
    cribes
    0.82
     прово
    0.79
    imwrite
    0.79
     facts
    0.78
    ข้อมูล
    0.77
    letek
    0.77
    丁寧
    0.77
    Activations Density 0.012%

    No Known Activations