© 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. 49828
    Prev
    Next
    INDEX
    Explanations

    html stylesheet links

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

    The neuron fires on HTML tags (especially `<link>` or `<script>`) that include external resources via attributes like `href=` or `src=` (e.g. linking a stylesheet or script file).

    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
     Чтобы
    -0.86
    火锅
    -0.85
    之助
    -0.79
     Как
    -0.79
     метал
    -0.77
    </b>
    -0.75
    купа
    -0.75
     disinformation
    -0.75
     Когда
    -0.73
    }_
    -0.72
    POSITIVE LOGITS
    css
    1.17
    Style
    1.04
     style
    0.96
     styling
    0.95
    bootstrap
    0.92
    style
    0.92
    getStyle
    0.92
     glyphicon
    0.90
    main
    0.88
    jquery
    0.86
    Activations Density 0.025%

    No Known Activations