© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10003
    Prev
    Next
    INDEX
    Explanations

    window.get, window., global

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

    browser window and document

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Il
    0.46
    ‥
    0.43
     Caucasian
    0.43
     Karg
    0.42
     badge
    0.39
     Cata
    0.39
     게
    0.38
     exhaust
    0.38
     fantasia
    0.38
    Caucasian
    0.38
    POSITIVE LOGITS
     window
    1.09
    window
    1.03
     Window
    0.89
    窓
    0.86
    窗口
    0.86
    Window
    0.82
     fenêtre
    0.82
    WINDOW
    0.80
     document
    0.75
     jendela
    0.73
    Activations Density 0.008%

    No Known Activations