© 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. 101551
    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
    paramInt
    -1.11
     donde
    -1.08
     tus
    -1.03
     primero
    -1.01
    levering
    -0.96
    の方は
    -0.96
     безопасность
    -0.94
    ы
    -0.93
     primera
    -0.89
    raisers
    -0.89
    POSITIVE LOGITS
     téměř
    1.03
     spezi
    0.98
     unemp
    0.97
     scammed
    0.96
     unmistak
    0.96
    を見た
    0.95
     ステンレス
    0.94
     cushioning
    0.94
     飾り
    0.92
     titans
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.