© 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. 104343
    Prev
    Next
    INDEX
    Explanations

    HTML table headers and code sections

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

    HTML table header tags (`<th>`) in code snippets.

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

    The neuron strongly activates on HTML table header tags (“<th>…”).

    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
    鋮
    -2.83
     or
    -2.70
     весна
    -2.36
    推荐阅读
    -2.16
    หรือ
    -2.11
    ;
    
    -2.11
    }
    -2.11
     福袋
    -2.09
    んでも
    -2.09
     even
    -2.08
    POSITIVE LOGITS
    {
    3.48
    <th>
    2.97
    can
    2.73
    Figure
    2.59
    ໌
    2.56
     cũng
    2.44
    饪
    2.42
    釤
    2.38
    up
    2.36
    </strong>
    2.34
    Activations Density 0.000%

    No Known Activations