© 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. 66961
    Prev
    Next
    INDEX
    Explanations

    code, scientific, or specific entities

    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
    ACCIÓN
    -1.25
    Zubereitung
    -1.15
     falda
    -1.05
     golos
    -1.04
    ього
    -1.04
    чта
    -1.03
     Milán
    -1.03
     Diputados
    -1.02
     Portail
    -1.01
     diserta
    -1.01
    POSITIVE LOGITS
    ant
    1.26
    ar
    1.08
    arn
    1.02
    ara
    0.97
     русской
    0.96
     principalement
    0.95
    なども
    0.95
    o
    0.94
    av
    0.93
    fa
    0.93
    Activations Density 0.000%

    No Known Activations