© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    Commence looking at figures

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

    job application answers

    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
     स्टूडेंट
    0.57
    striatis
    0.53
    ä
    0.49
     படி
    0.48
    圖像
    0.47
    žev
    0.47
     صحيح
    0.47
    Selecion
    0.47
     Thin
    0.46
    pubescens
    0.46
    POSITIVE LOGITS
    (^^
    0.50
    ’’
    0.46
     vui
    0.46
     kẻ
    0.46
    ря
    0.45
     quản
    0.44
    きち
    0.44
     nghịch
    0.43
    锣
    0.43
    ερ
    0.42
    Activations Density 0.000%

    No Known Activations