© 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. 24367
    Prev
    Next
    INDEX
    Explanations

    program and its description

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

    program

    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
    to
    0.84
    ).
    0.76
    EN
    0.74
    ं
    0.72
    v
    0.69
    ได้
    0.68
    il
    0.68
    <0x91>
    0.67
    bahan
    0.67
    بة
    0.65
    POSITIVE LOGITS
     programmi
    1.30
     프로그램
    1.29
     programu
    1.28
     programas
    1.21
     programma
    1.20
     programmes
    1.20
     програми
    1.20
     программы
    1.19
     برنامه
    1.16
     програ
    1.16
    Activations Density 0.059%

    No Known Activations