© 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. 118999
    Prev
    Next
    INDEX
    Explanations

    UI Controls

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

    the word "Controls" in code, particularly in namespace declarations and XAML markup for UI frameworks.

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

    The neuron fires on references to UI framework markup and namespaces—especially occurrences of “XAML” and “Controls” 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
     They
    -1.77
     trovano
    -1.68
    刘
    -1.61
    𖧵
    -1.54
    ↵
    -1.54
     mereka
    -1.48
     предпочита
    -1.46
            
    -1.41
    But
    -1.40
    コレクション
    -1.38
    POSITIVE LOGITS
     to
    2.22
     of
    1.68
     hordes
    1.61
    the
    1.59
    fortunately
    1.58
     gallons
    1.56
    摇了
    1.52
    媗
    1.52
     multitudes
    1.49
    iteľ
    1.48
    Activations Density 0.002%

    No Known Activations