© 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. 797
    Prev
    Next
    INDEX
    Explanations

    JavaScript function and app definitions

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

    This neuron activates on mentions of JavaScript frameworks, libraries, and related code‐API terms (e.g. React, Redux, Router, container, component).

    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
     MDLVertex
    0.75
    鲮
    0.73
    $&$
    0.64
    ploid
    0.64
    $\--
    0.63
    lbrakk
    0.63
    cellcolor
    0.62
    Convolution
    0.62
    鲫
    0.62
    zeugung
    0.61
    POSITIVE LOGITS
     BrowserRouter
    1.67
    BrowserRouter
    1.52
     React
    1.40
    ReactDOM
    1.38
     Routes
    1.35
     useEffect
    1.33
     routes
    1.30
    jsx
    1.30
     ROUTES
    1.30
    Routes
    1.29
    Activations Density 0.001%

    No Known Activations