© 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. 58157
    Prev
    Next
    INDEX
    Explanations

    first piece of information

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

    listing item separators

    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
     بق
    0.47
    بق
    0.46
    ayas
    0.45
     estaremos
    0.44
    ↵
    0.43
     ﺍﻟ
    0.42
    永远
    0.41
     تبقى
    0.40
    <b>
    0.40
     reelection
    0.39
    POSITIVE LOGITS
    多様
    0.47
     glancing
    0.46
    讼
    0.45
    ந்திர
    0.44
    勖
    0.44
    笏
    0.43
    鑑定
    0.42
    名を
    0.42
    newName
    0.42
    舧
    0.42
    Activations Density 0.000%

    No Known Activations