© 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. 254681
    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
    k
    0.52
     diminishing
    0.49
    o
    0.49
    葦
    0.48
    a
    0.48
    area
    0.47
     element
    0.47
     ए
    0.46
     項
    0.45
     financiera
    0.45
    POSITIVE LOGITS
    但也
    0.53
    жется
    0.48
    但我
    0.45
    গঠনিক
    0.45
    প্রে
    0.45
    उसके
    0.45
     जेव्हा
    0.44
    鹊
    0.43
     डेब्यू
    0.43
     тебя
    0.42
    Activations Density 0.002%

    No Known Activations