© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8273
    Prev
    Next
    INDEX
    Explanations

    window, windows

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

    window

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鳖
    0.45
    uchen
    0.40
     Avatar
    0.38
    arello
    0.38
    avat
    0.37
     phosphat
    0.35
    Cron
    0.35
    ahat
    0.35
     कोल्ड
    0.35
    跖
    0.35
    POSITIVE LOGITS
     window
    3.02
     windows
    2.86
     Window
    2.84
    window
    2.70
    窓
    2.70
    窗口
    2.69
    Window
    2.63
     WINDOW
    2.58
     jendela
    2.52
    窗
    2.52
    Activations Density 0.323%

    No Known Activations