© 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. 119458
    Prev
    Next
    INDEX
    Explanations

    HTML structural tags

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

    HTML semantic tags like header, nav, section, article, aside, footer, and main.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects HTML5 semantic sectioning elements (e.g. header, nav, main, section, article, aside, footer).

    oai_token-act-pair · o4-miniTriggered 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
     to
    -2.66
    牁
    -2.31
    蟶
    -2.11
    鼍
    -2.05
     referenced
    -1.88
    
    -1.88
     '
    -1.85
     \"
    -1.80
    桫
    -1.78
    付けた
    -1.77
    POSITIVE LOGITS
    m
    1.96
    1.89
    This
    1.76
    If
    1.70
    if
    1.69
    Примеча
    1.69
    这是一个
    1.66
    Интере
    1.65
    Извест
    1.65
    orteur
    1.64
    Activations Density 0.012%

    No Known Activations