© 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. 30373
    Prev
    Next
    INDEX
    Explanations

    React and Angular components

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

    This neuron detects React hook import specifiers—specifically the commas and braces used when destructuring hooks (e.g. useState) from the React import statement.

    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
    ופת
    -0.90
    otriva
    -0.86
     poète
    -0.83
    Rama
    -0.82
     Voyez
    -0.81
     نتيجة
    -0.81
     vanlig
    -0.81
     campeón
    -0.80
     harten
    -0.80
    錾
    -0.79
    POSITIVE LOGITS
     useEffect
    1.27
     use
    0.98
    there
    0.94
     There
    0.83
    (/*
    0.78
    潜力
    0.76
     creative
    0.75
    use
    0.75
    useEffect
    0.75
    创新
    0.74
    Activations Density 0.002%

    No Known Activations