© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210218
    Prev
    Next
    INDEX
    Explanations

    visit our store

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

    streams flowing

    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
    Вакансия
    0.49
     ン
    0.48
    ሰራ
    0.46
    wrong
    0.46
    ほか
    0.46
     Джу
    0.46
    ョン
    0.46
    奉
    0.45
    🤫
    0.45
    謐
    0.45
    POSITIVE LOGITS
     website
    0.47
     Page
    0.47
     pedibus
    0.46
     disulfide
    0.46
     situated
    0.45
     szk
    0.45
     Chlor
    0.44
     in
    0.44
     ¾
    0.44
     during
    0.44
    Activations Density 0.003%

    No Known Activations