© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7356
    Prev
    Next
    INDEX
    Explanations

    MQTT, tag, dropdown

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

    This neuron responds to mentions of graphical user‐interface elements (menus, toolbars, sliders, windows, 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_24_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
     Moringa
    0.68
    蛋白質
    0.67
    бні
    0.67
     பொருட்களை
    0.59
    overleftarrow
    0.59
    rainfall
    0.59
     பொருட்க
    0.57
    醗
    0.57
    timevals
    0.57
     ドライ
    0.56
    POSITIVE LOGITS
     buttons
    0.63
     menus
    0.60
     options
    0.59
     hijacking
    0.59
     veniam
    0.58
    条款
    0.56
     sağlan
    0.55
     prompted
    0.54
     hijack
    0.54
     öz
    0.54
    Activations Density 0.563%

    No Known Activations