© 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. 13889
    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
     who
    -0.96
    افظ
    -0.96
     भार
    -0.92
    違って
    -0.90
    ように
    -0.89
     praktis
    -0.87
    延伸
    -0.86
    ́n
    -0.86
    \}
    -0.85
    лад
    -0.85
    POSITIVE LOGITS
    を書いて
    1.09
     isolado
    1.06
    ónicos
    1.04
     systému
    0.95
     Шаг
    0.93
     produkty
    0.93
     chère
    0.92
    つい
    0.90
    ابراین
    0.89
     merveille
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.