© 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. 39051
    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
     '
    -1.88
    ↵
    -1.86
     perigo
    -1.84
     You
    -1.84
     that
    -1.84
     
    -1.76
     discreet
    -1.73
     Other
    -1.71
     márm
    -1.67
     silêncio
    -1.66
    POSITIVE LOGITS
     Atención
    1.91
     Boletín
    1.77
     lakini
    1.77
    iseen
    1.73
     extraordinaire
    1.71
    禤
    1.66
     Agosto
    1.63
     carcasa
    1.61
     заба
    1.60
     XXXII
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.