© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106305
    Prev
    Next
    INDEX
    Explanations

    URL paths and configurations

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

    The neuron strongly activates on JSX/HTML tag tokens—especially React Router `<Route>` elements and their key attributes like “path,” “component,” “url,” and “id.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     APPLICATION
    -0.85
    ゐ
    -0.79
     Sanitation
    -0.78
    ittoria
    -0.76
    深渊
    -0.76
    Răspunde
    -0.75
    ()),
    -0.73
     relazione
    -0.73
     Application
    -0.72
     alimen
    -0.72
    POSITIVE LOGITS
    ="/
    1.07
     "/
    0.90
    llar
    0.88
    ㈜
    0.83
     ":
    0.81
    ("*
    0.80
     antara
    0.79
    Debra
    0.77
     Genau
    0.77
    詠
    0.77
    Activations Density 0.001%

    No Known Activations