© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257169
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ต์
    0.53
     חי
    0.53
     ܒ
    0.53
     Архі
    0.52
     უფრო
    0.50
     może
    0.49
     רק
    0.49
     лише
    0.49
     יותר
    0.49
     “[
    0.49
    POSITIVE LOGITS
    лын
    0.50
     Computer
    0.48
     kitchens
    0.46
     marines
    0.46
     beaches
    0.46
    پ
    0.46
    У
    0.46
    in
    0.46
    را
    0.46
     Carpet
    0.46
    Activations Density 0.000%

    No Known Activations