© 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. 10-GEMMASCOPE-RES-131K
    4. 11621
    Prev
    Next
    INDEX
    Explanations

    html hr tag and hours

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

    the abbreviation "hr" in technical or data contexts (representing "hour" or appearing in code/data fields).

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

    The neuron is specialized to detect the HTML horizontal‐rule tag (“<hr>”).

    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
    昻
    -3.30
    bánh
    -2.84
    杙
    -2.81
    噲
    -2.80
    疴
    -2.75
    懨
    -2.66
    䊐
    -2.61
    饃
    -2.61
    いって
    -2.58
     遇
    -2.55
    POSITIVE LOGITS
    *
    3.95
    hr
    3.66
    re
    3.61
    on
    3.41
    li
    3.38
    ed
    3.31
    ra
    3.23
    si
    3.22
    se
    3.19
    h
    3.19
    Activations Density 0.007%

    No Known Activations