© 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. 5979
    Prev
    Next
    INDEX
    Explanations

    select menu item

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

    The neuron strongly activates on words referring to menu or navigation UI elements (e.g. “menu,” “navigation,” “link,” “childNav,” etc.).

    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
     aug
    0.60
     stroj
    0.60
    忪
    0.59
    मिट
    0.55
     કબ
    0.55
     العلا
    0.55
     środków
    0.53
     тка
    0.53
    駝
    0.53
     Champagne
    0.52
    POSITIVE LOGITS
     submenu
    1.88
    submenu
    1.72
     menu
    1.63
     메뉴
    1.57
    Menu
    1.53
    menu
    1.53
    MenuItem
    1.53
     MenuItem
    1.52
     меню
    1.52
     menuItem
    1.52
    Activations Density 0.062%

    No Known Activations