© 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. 10-GEMMASCOPE-RES-131K
    4. 127211
    Prev
    Next
    INDEX
    Explanations

    UI components and forms

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

    This neuron detects mentions of UI components (widget/control class names) in code, such as “widget,” “Form,” “Layout,” or specific view identifiers like “imageView.”

    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
     VERY
    -1.54
     tamaños
    -1.53
     REALLY
    -1.53
    iciaries
    -1.48
    ᠋
    -1.40
     ALREADY
    -1.38
    螃
    -1.38
     může
    -1.38
     SMALL
    -1.37
    륭
    -1.35
    POSITIVE LOGITS
     all
    1.86
     would
    1.81
     for
    1.79
     from
    1.64
     could
    1.63
     Since
    1.61
     through
    1.48
     seems
    1.47
     at
    1.43
     of
    1.42
    Activations Density 0.004%

    No Known Activations