© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41261
    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
    PLICATIONS
    -1.05
     iliy
    -1.00
    RV
    -0.97
     Einkommen
    -0.96
     劉
    -0.96
     számára
    -0.94
     theres
    -0.93
     鈴木
    -0.91
    squareup
    -0.91
    ił
    -0.91
    POSITIVE LOGITS
     обладает
    0.96
     degree
    0.93
    うちに
    0.91
    しなければ
    0.88
     ética
    0.87
    だったので
    0.86
    又は
    0.84
     
    0.82
    があり
    0.81
    mathematics
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.