© 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. 129910
    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
    ୈ
    -1.09
     that
    -1.05
     which
    -1.02
    🦄
    -0.98
     kvad
    -0.98
    ‏‏
    -0.97
    XI
    -0.97
     vekt
    -0.96
    getJSONObject
    -0.94
     soal
    -0.93
    POSITIVE LOGITS
    บัติ
    0.98
     buscan
    0.95
     movimenta
    0.91
     discrepancies
    0.90
    verbosity
    0.88
    嚕
    0.88
     jj
    0.86
     erkannt
    0.85
    UVEN
    0.85
     indicative
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.