© 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. 34-GEMMASCOPE-RES-131K
    4. 83216
    Prev
    Next
    INDEX
    Explanations

    frontend component tags

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

    This neuron fires on the “<” token (and related markup delimiters), i.e. the beginnings of HTML/JSX/XML tags.

    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
     प्रत्येक
    -0.91
    paramref
    -0.86
     disampaikan
    -0.85
     puh
    -0.82
    even
    -0.79
    jada
    -0.79
    рений
    -0.78
    opera
    -0.78
     Даже
    -0.78
     व्यक्ति
    -0.77
    POSITIVE LOGITS
    div
    1.43
    <>
    1.11
     divorce
    0.93
     alegre
    0.92
     <>
    0.88
     Div
    0.87
    Div
    0.85
    attaa
    0.83
    React
    0.79
     vertes
    0.79
    Activations Density 0.004%

    No Known Activations