© 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. 163734
    Prev
    Next
    INDEX
    Explanations

    questions, orders, and actions

    np_acts-logits-general · gemini-2.5-flash-lite

    capacity constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    厕
    0.53
    명
    0.50
    чка
    0.49
    명이
    0.49
    
    0.47
    ثت
    0.46
    ืช
    0.46
     cellul
    0.45
    愁
    0.45
     inser
    0.45
    POSITIVE LOGITS
     Liberation
    0.49
     XI
    0.49
     परिभाषा
    0.48
     Pointer
    0.48
     Durham
    0.47
     branded
    0.46
     इमारत
    0.44
     Lib
    0.43
     Navigation
    0.43
     Fondo
    0.43
    Activations Density 0.001%

    No Known Activations