© 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. 113784
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    s
    -2.02
    re
    -1.73
    t
    -1.68
    `
    -1.66
    isation
    -1.65
    ...
    -1.59
    ts
    -1.56
    ched
    -1.55
    right
    -1.54
    --
    -1.53
    POSITIVE LOGITS
     kağıdı
    1.85
     kiedyś
    1.73
     aplicar
    1.73
    齎
    1.66
    榖
    1.61
     recentes
    1.60
    𑁍
    1.55
     diciembre
    1.55
     adventurer
    1.55
     that
    1.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.