© 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. 116859
    Prev
    Next
    INDEX
    Explanations

    script tags and paths

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

    This neuron detects HTML resource‐loading attributes, especially URLs in link and script tags (e.g. href, src, protocol and domain parts).

    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
    lė
    -0.75
    pric
    -0.74
     Blinds
    -0.73
    ttp
    -0.70
     compuestos
    -0.70
    fahrt
    -0.70
     Tort
    -0.69
     ETL
    -0.69
     Smarty
    -0.69
     没
    -0.68
    POSITIVE LOGITS
    static
    1.16
    assets
    1.08
     scripts
    1.06
     script
    0.95
     assets
    0.93
     static
    0.93
    "></
    0.90
    cripts
    0.90
    script
    0.87
    Script
    0.87
    Activations Density 0.065%

    No Known Activations