© 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. 48026
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tags

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

    The neuron activates on markup tokens (e.g. HTML/XML tags, attributes, and entities) in the text.

    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
    ↵
    -1.94
     a
    -1.80
     レ
    -1.69
     has
    -1.63
     was
    -1.58
     the
    -1.57
    ’，
    -1.55
     may
    -1.52
     presents
    -1.49
     ラ
    -1.48
    POSITIVE LOGITS
    ING
    1.90
    "../
    1.87
     winkel
    1.71
    tuar
    1.70
     mensual
    1.70
     goûts
    1.65
    insulin
    1.64
    \
    1.63
     stål
    1.63
    already
    1.63
    Activations Density 0.000%

    No Known Activations