© 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. 104083
    Prev
    Next
    INDEX
    Explanations

    medical procedures and body parts

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

    learns specific good

    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
     paren
    0.54
    ン
    0.54
    rentes
    0.51
     ヴィンテージ
    0.51
    が大
    0.51
    ن
    0.51
    ရင်း
    0.48
    asses
    0.47
     친
    0.47
     صوت
    0.47
    POSITIVE LOGITS
    覆盖
    0.47
    λικό
    0.47
    YOU
    0.45
    顺利
    0.43
    观看
    0.43
    Tonight
    0.43
     Magnificent
    0.43
    穹
    0.43
    ঙ্গা
    0.43
    ¯
    0.43
    Activations Density 0.000%

    No Known Activations