© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99120
    Prev
    Next
    INDEX
    Explanations

    UI elements and code initialization

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

    The neuron fires on code tokens that set or reference UI text properties or methods (e.g. “text”, “setTitle”, “setSubtitle”).

    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
     Durand
    -0.72
    รก
    -0.71
     deinen
    -0.71
     გ
    -0.71
    <\
    -0.67
    xd
    -0.67
     заяв
    -0.67
     завода
    -0.66
    arc
    -0.66
    DMA
    -0.65
    POSITIVE LOGITS
     colour
    0.93
     color
    0.88
    color
    0.76
    ichtung
    0.75
    Color
    0.74
     Color
    0.71
     pidiendo
    0.71
    Colour
    0.71
    colour
    0.70
    veri
    0.69
    Activations Density 0.037%

    No Known Activations