© 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. 8189
    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
    Apakah
    -1.06
    ABASES
    -1.05
    Untuk
    -1.03
    Kegiatan
    -1.00
     dzī
    -0.96
    rierten
    -0.95
    Kondisi
    -0.94
    Karena
    -0.94
    Mengapa
    -0.94
    ()};
    -0.93
    POSITIVE LOGITS
    o
    0.97
    ma
    0.90
     sắc
    0.90
     also
    0.85
     ’
    0.84
    z
    0.84
    ya
    0.83
    ELS
    0.82
    E
    0.82
    どんどん
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.