© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30330
    Prev
    Next
    INDEX
    Explanations

    react router browser history

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

    The neuron activates on tokens related to JavaScript/React routing libraries or router API calls (e.g. “react-router-dom,” `<Router>`, `useHistory`, `reach/router`, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icace
    -0.76
     logical
    -0.76
     lover
    -0.75
    phyllum
    -0.75
     cau
    -0.73
     signUp
    -0.72
     fore
    -0.72
     предприятия
    -0.71
     neque
    -0.71
    aguay
    -0.71
    POSITIVE LOGITS
     Browser
    0.95
     historians
    0.90
    Glück
    0.89
     AGUA
    0.83
     BrowserRouter
    0.82
    browser
    0.81
    Matéri
    0.80
    Dank
    0.79
     embreagem
    0.79
     browser
    0.79
    Activations Density 0.003%

    No Known Activations