© 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. 72728
    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
    老師
    -0.93
    ং
    -0.92
    </i>
    -0.90
    ном
    -0.90
    qing
    -0.89
    s
    -0.89
     plexus
    -0.88
    UnknownFields
    -0.87
     jeden
    -0.86
    </td>
    -0.86
    POSITIVE LOGITS
    IANI
    0.94
     škole
    0.90
     bazı
    0.88
     brąz
    0.88
    訴
    0.87
     unterschied
    0.86
     coincided
    0.86
     विभिन्न
    0.85
     deň
    0.85
     amounted
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.