© 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. 175129
    Prev
    Next
    INDEX
    Explanations

    specific examples and their consequents

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

    roles and notes

    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
     Dalib
    0.49
    важа
    0.47
     Гинд
    0.46
    Ы
    0.45
    лык
    0.45
    Deps
    0.45
     pós
    0.44
     ок
    0.44
    ぇ
    0.44
    の方法
    0.43
    POSITIVE LOGITS
    时间
    0.49
     atyp
    0.47
     时间
    0.47
    usions
    0.46
     unexpected
    0.45
    مل
    0.44
     remnants
    0.44
    文件名
    0.44
    魟
    0.43
     带
    0.42
    Activations Density 0.000%

    No Known Activations