© 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. 34-GEMMASCOPE-RES-131K
    7. 119213
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

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

    This neuron detects HTML structural tags (e.g. heading tags like <h1> or <h2> and table tags such as <table> or <td>).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ></
    -1.20
    "></
    -1.17
     these
    -1.05
    \"></
    -0.98
    =""></
    -0.96
    '></
    -0.94
    These
    -0.94
    </
    -0.93
     stating
    -0.89
    <h4>
    -0.86
    POSITIVE LOGITS
     baseado
    1.02
     skolan
    0.94
    ᒪ
    0.92
     suministros
    0.90
     artigos
    0.90
    ریزی
    0.89
     encuentros
    0.88
    HPP
    0.88
    MMP
    0.87
    יהם
    0.87
    Activations Density 0.005%

    No Known Activations