© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6967
    Prev
    Next
    INDEX
    Explanations

    HTML tags

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

    This neuron activates on HTML/XML markup delimiters (the “<” that introduces tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marginTop
    0.76
    newpage
    0.74
    <body>
    0.67
     subheading
    0.64
     située
    0.59
     गर्दन
    0.58
    <tfoot>
    0.58
     Bowman
    0.57
    <tr>
    0.57
    modal
    0.57
    POSITIVE LOGITS
     الأولى
    0.64
    !!!");
    0.56
    Periods
    0.55
    ！！！！
    0.55
    IVER
    0.54
    РО
    0.54
    ！！！
    0.52
    !!");
    0.52
    DataProvider
    0.51
    უნ
    0.50
    Activations Density 0.002%

    No Known Activations