© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3177
    Prev
    Next
    INDEX
    Explanations

    arranges windows

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

    The neuron spots mentions of “window,” especially in technical or API/UI contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     سعودی
    0.62
     भेद
    0.55
     itemprop
    0.55
     Faith
    0.54
     polysaccharides
    0.54
     Pathol
    0.53
     डीएनए
    0.53
    荥
    0.52
    ्यानंतर
    0.51
    볶
    0.51
    POSITIVE LOGITS
     window
    2.08
    窗口
    2.02
     Window
    2.00
    ウィンドウ
    1.98
    Window
    1.97
    window
    1.88
     окна
    1.80
     janela
    1.79
    WINDOW
    1.78
     ventana
    1.73
    Activations Density 0.265%

    No Known Activations