© 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. 10-GEMMASCOPE-RES-131K
    7. 68352
    Prev
    Next
    INDEX
    Explanations

    dominance or extreme success

    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_10/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
    
    -1.70
     ་
    -1.65
    řízení
    -1.63
     einwand
    -1.55
    ricanes
    -1.54
    lho
    -1.48
    驺
    -1.45
     calificaciones
    -1.42
     faciliter
    -1.41
    蛱
    -1.40
    POSITIVE LOGITS
     in
    1.93
     with
    1.85
     on
    1.83
     at
    1.38
    m
    1.32
    t
    1.27
     providing
    1.25
     &
    1.23
     without
    1.22
     by
    1.17
    Activations Density 0.038%

    No Known Activations