© 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. 101125
    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
     минима
    -1.00
     Question
    -0.94
     vistos
    -0.93
     wenige
    -0.91
     mineures
    -0.91
    </h5>
    -0.90
     kolay
    -0.88
     reglas
    -0.88
     vorgesehen
    -0.87
     Waiting
    -0.86
    POSITIVE LOGITS
     LIBRARIES
    1.00
     Hecho
    1.00
    moreland
    0.95
     anonyme
    0.93
    本日の
    0.91
     См
    0.91
     with
    0.91
     finner
    0.90
     forestal
    0.90
     legendar
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.