© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10267
    Prev
    Next
    INDEX
    Explanations

    UI components and layout

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

    This neuron activates on capitalized code identifiers and UI component names (e.g. React/Angular component names, dropdown/menu class names, ARIA attribute terms).

    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
    iciencia
    0.66
    userName
    0.64
    :"",
    0.63
    buttonclick
    0.62
    تیب
    0.62
     userdata
    0.62
     rougeâtres
    0.61
     ورق
    0.60
    ريقة
    0.60
     માંગ
    0.59
    POSITIVE LOGITS
     component
    0.61
     primitive
    0.54
     nir
    0.54
    ]^
    0.54
     intrinsically
    0.54
     scrim
    0.54
     skept
    0.54
     illust
    0.53
     maxim
    0.52
    áv
    0.52
    Activations Density 0.003%

    No Known Activations