© 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. 10-GEMMASCOPE-RES-131K
    7. 85085
    Prev
    Next
    INDEX
    Explanations

    bootstrap, vascular, min.css

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

    The neuron is triggered by references to Bootstrap’s CSS files—especially CDN link URLs and their version numbers (e.g. “bootstrap.min.css” with “3.x.x” versions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to the Bootstrap CSS framework, especially CDN stylesheet links, versioned filenames, and mentions of Bootstrap components and issues.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to Bootstrap CSS framework files and version numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ⅽ
    -1.29
    one
    -1.29
     delapan
    -1.27
     desapar
    -1.26
    eno
    -1.26
     each
    -1.26
     "
    -1.26
    。"
    -1.24
     from
    -1.23
     then
    -1.23
    POSITIVE LOGITS
    occuper
    1.41
    Warto
    1.40
     seguras
    1.30
     externas
    1.28
     básicas
    1.26
     internas
    1.26
    Елена
    1.25
     فيها
    1.21
     urbanas
    1.20
     parede
    1.19
    Activations Density 0.012%

    No Known Activations