© 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. 10-GEMMASCOPE-RES-131K
    7. 12802
    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
    a
    -1.15
     versions
    -1.12
    Й
    -1.05
    Version
    -1.04
    count
    -0.98
    vetica
    -0.96
    В
    -0.94
    er
    -0.94
    FIX
    -0.94
    arg
    -0.94
    POSITIVE LOGITS
     DCT
    1.02
     Pfar
    0.96
    ल्स
    0.96
    posicion
    0.95
    pieza
    0.94
    🧸
    0.93
    fır
    0.93
     Američ
    0.91
    humble
    0.90
     gudang
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.