© 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. 34-GEMMASCOPE-RES-131K
    4. 90480
    Prev
    Next
    INDEX
    Explanations

    Java GUI component names

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

    This neuron fires on Java Swing code snippets—especially tokens from Swing API calls and class names like JProgressBar, getInputMap, put, etc.

    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
     istnieje
    -0.74
     volunteered
    -0.72
     Limestone
    -0.72
     handles
    -0.71
    engibre
    -0.69
    ừa
    -0.69
     кро
    -0.69
    ਾਲ
    -0.67
    heast
    -0.67
     überzeugen
    -0.67
    POSITIVE LOGITS
    getAction
    0.92
    URU
    0.89
    INET
    0.82
     Chandigarh
    0.79
    insular
    0.79
    clients
    0.79
    "){
    
    0.77
    jimo
    0.75
    Formatted
    0.75
    getClient
    0.75
    Activations Density 0.014%

    No Known Activations