© 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. 94495
    Prev
    Next
    INDEX
    Explanations

    specific data

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

    multi-language correspondence

    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
    Для
    0.56
    ミア
    0.54
    ショッピング
    0.52
    リ
    0.50
    チャレンジ
    0.49
    Czas
    0.49
    ード
    0.48
    な
    0.48
     ainult
    0.48
    ハ
    0.47
    POSITIVE LOGITS
    নির্ম
    0.45
     العمود
    0.44
     décider
    0.44
     khẳng
    0.43
     Awards
    0.43
     HUGH
    0.43
     cử
    0.42
     đã
    0.42
     Hershey
    0.42
     JAMA
    0.42
    Activations Density 0.001%

    No Known Activations