© 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. 123891
    Prev
    Next
    INDEX
    Explanations

    life events and occasions

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

    building connection, development

    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
    Negative Logits
    マンス
    0.48
    の設定
    0.48
     ха
    0.47
    ncia
    0.47
    ﺷ
    0.44
    ная
    0.43
     enabled
    0.43
    ジャパン
    0.43
     согласо
    0.43
    淉
    0.43
    POSITIVE LOGITS
    لیکن
    0.50
     Funeral
    0.50
     feste
    0.48
     annivers
    0.48
     birthdays
    0.47
     funeral
    0.47
     rigid
    0.46
     behöver
    0.45
     Bedür
    0.45
     Celebrating
    0.44
    Activations Density 0.002%

    No Known Activations