© 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. 33932
    Prev
    Next
    INDEX
    Explanations

    performance metrics

    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
     still
    -1.30
     things
    -1.03
    neuf
    -1.02
     about
    -1.00
     Staffel
    -1.00
    «
    -0.97
    лен
    -0.97
     σήμερα
    -0.96
     露
    -0.96
    ($("#
    -0.95
    POSITIVE LOGITS
     quí
    1.19
    Реги
    1.14
     percentage
    1.08
    鉺
    1.06
    Datenschutz
    1.05
    gangenen
    1.05
    Melon
    1.04
    idespread
    1.03
    cún
    1.03
     degré
    1.02
    Activations Density 0.004%

    No Known Activations