© 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. 22-GEMMASCOPE-RES-131K
    7. 38962
    Prev
    Next
    INDEX
    Explanations

    for a review

    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_22/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
     if
    -1.20
    他有
    -1.03
     when
    -1.00
     pastikan
    -0.98
     garansi
    -0.95
    роде
    -0.93
     pidió
    -0.93
     pubblica
    -0.92
     pengiriman
    -0.92
     like
    -0.91
    POSITIVE LOGITS
    ยะ
    1.08
     allé
    1.05
    xem
    1.00
    чные
    1.00
    quête
    0.99
     utom
    0.98
    VIRGO
    0.98
    関する
    0.97
    骨折
    0.96
     déclar
    0.94
    Activations Density 0.020%

    No Known Activations