© 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. 22-GEMMASCOPE-RES-131K
    7. 65831
    Prev
    Next
    INDEX
    Explanations

    synthesize, enum, const, variable, host

    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
     dépenses
    -1.17
    🍯
    -1.12
     futu
    -1.08
    Нау
    -1.06
    Τα
    -1.05
    urrection
    -1.05
    ✔️
    -1.04
     مراحل
    -1.03
     ヌード
    -1.02
    炱
    -1.02
    POSITIVE LOGITS
     such
    1.11
     „
    1.11
    vateľov
    1.06
     number
    1.02
     categories
    1.01
    %;">
    0.99
     sirven
    0.98
     estás
    0.97
     Strength
    0.95
     all
    0.94
    Activations Density 0.072%

    No Known Activations