© 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. 9167
    Prev
    Next
    INDEX
    Explanations

    HTML tags

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

    This neuron detects HTML/XML markup tags (e.g. “</a>”, “<div>”, “<A href=…>”).

    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
     Django
    0.57
     Acá
    0.56
     Gauge
    0.54
    🙈
    0.54
     Expansion
    0.54
     Slots
    0.54
    \!\
    0.54
     ellas
    0.53
    }`}
    0.53
    \!
    0.53
    POSITIVE LOGITS
    რების
    0.61
    说法
    0.60
    of
    0.59
    modified
    0.57
    deposit
    0.55
    爲
    0.53
    LogLevel
    0.51
    *,
    0.51
    मुक्त
    0.51
    setIs
    0.50
    Activations Density 0.006%

    No Known Activations