© 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. 75661
    Prev
    Next
    INDEX
    Explanations

    downloading media and business

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

    and, with, or

    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
     Omphalodes
    0.57
    dimensioni
    0.56
    𝐍
    0.55
     पर्यावरणीय
    0.54
    لیم
    0.54
     हिटलर
    0.54
     設定
    0.52
     ۔۔۔
    0.52
    <unused52>
    0.52
    IdleSync
    0.52
    POSITIVE LOGITS
     drug
    0.48
    we
    0.48
     to
    0.47
     thought
    0.46
     AI
    0.46
     Dura
    0.46
     of
    0.45
     music
    0.45
     treatment
    0.45
     #
    0.45
    Activations Density 0.001%

    No Known Activations