© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105536
    Prev
    Next
    INDEX
    Explanations

    UI buttons and CVD methods

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

    references to UI button objects or button-related code in technical programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects occurrences of the class name “UIButton” in code.

    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
    岀
    -2.50
     یا
    -2.50
    -2.47
    缎
    -2.33
    將軍
    -2.25
     ול
    -2.25
    这里
    -2.25
    able
    -2.23
     الجديدة
    -2.20
     verändern
    -2.20
    POSITIVE LOGITS
    畯
    3.20
    诹
    2.81
    t
    2.80
     were
    2.70
    辔
    2.53
    了的
    2.53
    珢
    2.48
    齷
    2.47
     a
    2.44
    に於
    2.42
    Activations Density 0.003%

    No Known Activations