© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63672
    Prev
    Next
    INDEX
    Explanations

    HTML tags

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

    The neuron fires strongly on HTML/XML tag names (the words inside `<` and `>`).

    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
    liquidity
    -0.79
    Să
    -0.77
    Prí
    -0.75
    原文
    -0.75
    羧
    -0.74
     Plattform
    -0.73
    Reklama
    -0.73
    onomia
    -0.73
     relevant
    -0.72
    ießen
    -0.69
    POSITIVE LOGITS
    <h3>
    1.85
    <h4>
    1.84
    <h5>
    1.66
    <h2>
    1.63
    <h6>
    1.57
    <table>
    1.56
    <tr>
    1.54
    <h1>
    1.40
    <th>
    1.30
    <caption>
    1.21
    Activations Density 0.089%

    No Known Activations