© 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. 130468
    Prev
    Next
    INDEX
    Explanations

    code structures and scenarios

    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
    psons
    -0.95
     réinitial
    -0.91
     professores
    -0.90
    igot
    -0.88
    スコ
    -0.85
    bbi
    -0.85
     same
    -0.85
     predominantly
    -0.84
     Pipes
    -0.83
    numerator
    -0.83
    POSITIVE LOGITS
    Друзья
    0.86
     {'
    0.80
    Новые
    0.79
    0.79
    gunaan
    0.76
    логические
    0.76
    ungkap
    0.75
    pektor
    0.75
    Эти
    0.75
     interess
    0.75
    Activations Density 0.022%

    No Known Activations