© 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. 34-GEMMASCOPE-RES-131K
    7. 57630
    Prev
    Next
    INDEX
    Explanations

    redistribute or modify software

    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_34/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
     følge
    -0.84
     بتاريخ
    -0.83
    казания
    -0.82
    塑造
    -0.80
     знаем
    -0.79
     officiel
    -0.77
    lateur
    -0.77
    RuleContext
    -0.77
     жена
    -0.74
     interpretar
    -0.73
    POSITIVE LOGITS
     sideboard
    1.72
    Side
    1.34
     Side
    1.16
     sided
    1.10
     side
    1.03
     substitu
    0.96
     sostitu
    0.95
     siding
    0.95
    SIDE
    0.93
     SIDE
    0.91
    Activations Density 0.003%

    No Known Activations