© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108955
    Prev
    Next
    INDEX
    Explanations

    import or specific phrases

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

    The neuron strongly activates on JavaScript/TypeScript import statements—especially React-related imports (import, from, the braces around named imports, and common React hooks or symbols).

    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
     useState
    -0.85
     since
    -0.84
     juntas
    -0.84
    ὼ
    -0.81
     Entrega
    -0.78
    жаться
    -0.78
     any
    -0.77
     StatelessWidget
    -0.76
     configureStore
    -0.76
     اللہ
    -0.75
    POSITIVE LOGITS
     axios
    0.94
    axios
    0.86
     forgery
    0.81
    龋
    0.78
    ⮞
    0.78
    페
    0.77
    лық
    0.76
    thentic
    0.75
     mulberry
    0.74
    PRET
    0.73
    Activations Density 0.003%

    No Known Activations