© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80676
    Prev
    Next
    INDEX
    Explanations

    bootstrap ui framework

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

    The neuron fires on references to library asset filenames—especially Bootstrap (and related plugin) CSS/JS file names and versioned paths (e.g. “bootstrap.min.css,” “bootstrapcdn.com/.../bootstrap/3.x.x.min.css,” “datetimepicker”).

    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
     antar
    -0.82
    ПЕ
    -0.80
    ,-
    -0.77
    гата
    -0.77
    abilities
    -0.77
    ເ
    -0.76
     الاحتلال
    -0.75
     macOS
    -0.75
     Ludo
    -0.73
    ToString
    -0.73
    POSITIVE LOGITS
     Bootstrap
    0.85
     grazia
    0.83
    ضان
    0.82
    ₚ
    0.72
     Kunde
    0.72
     уверен
    0.72
    taps
    0.71
    umuz
    0.71
    意思
    0.70
     Boots
    0.70
    Activations Density 0.021%

    No Known Activations