© 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. 102632
    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
     EEUU
    -1.05
    abbr
    -1.02
    mitteilung
    -0.97
    thebibliography
    -0.94
    かります
    -0.91
     Toilette
    -0.89
     miłości
    -0.88
    rétaire
    -0.88
     Tinggi
    -0.88
    熨
    -0.87
    POSITIVE LOGITS
    ragona
    1.07
     gelangen
    0.97
     thịt
    0.97
     aktivieren
    0.95
    identified
    0.88
    wegian
    0.87
     vorstellen
    0.87
     ziet
    0.87
    感到
    0.85
    8
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.