© 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. 146846
    Prev
    Next
    INDEX
    Explanations

    privacy is important

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

    how it breaks down

    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
    infix
    0.46
     vuttam
    0.46
    はじめ
    0.44
    GTEST
    0.44
     noemen
    0.43
    千萬
    0.43
    ライ
    0.42
    jhelp
    0.42
    졔
    0.41
    惹
    0.41
    POSITIVE LOGITS
     Parking
    0.48
     gratitude
    0.47
     their
    0.46
     επισ
    0.45
     Gasoline
    0.45
     PAR
    0.45
    停车场
    0.45
     parking
    0.44
    Grat
    0.44
     Relationship
    0.44
    Activations Density 0.001%

    No Known Activations