© 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. 22-GEMMASCOPE-RES-131K
    7. 67626
    Prev
    Next
    INDEX
    Explanations

    html/template tags

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

    The neuron strongly responds to HTML markup elements—especially opening tag names like div, section, script, style, etc.—marking the structure of an HTML document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -1.17
    bernate
    -1.06
    washingtonpost
    -1.05
    seros
    -1.05
    えられる
    -1.03
     Nhưng
    -1.00
     cucchia
    -0.99
    ləş
    -0.99
    ATTRIBUTE
    -0.98
    wyr
    -0.98
    POSITIVE LOGITS
     at
    1.27
    ánd
    1.01
     unless
    1.00
     перед
    1.00
    手帳
    1.00
    oa̍t
    0.97
     you
    0.94
     before
    0.94
     вашу
    0.94
     if
    0.92
    Activations Density 0.028%

    No Known Activations