© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8556
    Prev
    Next
    INDEX
    Explanations

    UI component attributes and tags

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

    This neuron activates on JSX/HTML tag or component names (i.e. the element identifiers in angle-bracketed 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_10/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
     obce
    -1.91
    Ils
    -1.90
    Spesifikasi
    -1.88
     guapa
    -1.87
     作り方
    -1.86
    فیلم
    -1.85
    besondere
    -1.82
    مقدمه
    -1.82
     sanoo
    -1.80
    Подготовка
    -1.79
    POSITIVE LOGITS
    [
    2.31
     is
    2.03
    </i>
    1.90
    y
    1.76
    e
    1.74
     among
    1.73
     marseille
    1.72
    ";
    1.67
     according
    1.65
    umers
    1.63
    Activations Density 0.007%

    No Known Activations