© 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. 84118
    Prev
    Next
    INDEX
    Explanations

    jquery and bootstrap versions

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

    This neuron recognizes numeric version identifiers (digit sequences and decimals) in library URLs and import statements.

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

    version numbers in file paths and URLs, particularly for jQuery library references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    HTML snippets that reference external JavaScript libraries via versioned CDN URLs and related markup (e.g., script includes and metadata tags).

    oai_token-act-pair · gpt-5Triggered 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
    jointed
    -0.90
    مصادر
    -0.85
     dominar
    -0.79
     still
    -0.79
    рой
    -0.77
     Heilig
    -0.75
     grijs
    -0.74
    정보
    -0.73
     itself
    -0.73
    lägen
    -0.73
    POSITIVE LOGITS
    mainloop
    0.72
    glicher
    0.70
     Archibald
    0.69
    폰
    0.69
     getestet
    0.69
    Clerk
    0.69
    (!(
    0.68
    slim
    0.68
    bijt
    0.66
    ismu
    0.66
    Activations Density 0.012%

    No Known Activations