© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92477
    Prev
    Next
    INDEX
    Explanations

    React

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

    The neuron fires on tokens in module import statements—especially the parts around “from '…'” (e.g. the quoted paths and key import names like React/useEffect).

    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
     beneath
    -0.76
     Armies
    -0.75
     other
    -0.74
     televised
    -0.73
     Mortal
    -0.72
    itology
    -0.71
     declared
    -0.69
     Kinh
    -0.69
     Mannes
    -0.68
     class
    -0.67
    POSITIVE LOGITS
     React
    0.98
     useEffect
    0.94
    nytt
    0.94
    hooks
    0.91
    Hooks
    0.88
    QMessageBox
    0.88
    alamualaikum
    0.88
    glą
    0.87
     pisos
    0.86
    catchError
    0.84
    Activations Density 0.004%

    No Known Activations