© 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. 7733
    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
    etes
    0.54
    WAY
    0.52
    ars
    0.49
    MD
    0.48
    usik
    0.48
    s
    0.48
    =="
    0.48
     ETL
    0.47
    uset
    0.47
    ANS
    0.47
    POSITIVE LOGITS
    み
    0.51
    勝ち
    0.50
     личности
    0.50
    ைத்
    0.49
    Ꮼ
    0.49
    の開発
    0.48
    读者
    0.47
    વા
    0.47
     поведение
    0.46
     жизнью
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.