© 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. 21906
    Prev
    Next
    INDEX
    Explanations

    java util property access

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

    The neuron detects occurrences of the substring “util” (e.g. in package or file paths).

    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
    但
    -1.97
    ")){
    
    -1.93
     zweiter
    -1.87
    "]),
    -1.87
    '}),
    -1.83
    _;
    
    -1.80
    tonsoft
    -1.78
    '
    -1.73
     According
    -1.72
    --;
    
    -1.72
    POSITIVE LOGITS
    a
    1.95
     gracefully
    1.94
     besos
    1.82
     recevrez
    1.78
     墊
    1.72
     abiye
    1.70
     aurez
    1.69
     gonna
    1.69
     Lombardia
    1.68
    
    1.67
    Activations Density 0.003%

    No Known Activations