© 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. 34-GEMMASCOPE-RES-131K
    7. 37782
    Prev
    Next
    INDEX
    Explanations

    java.util.Scanner usage

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

    This neuron detects Java import statements (especially imports from java.util, like Scanner).

    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
     without
    -0.88
     list
    -0.71
    честве
    -0.69
    ⋈
    -0.68
    usul
    -0.67
    🥼
    -0.66
     списка
    -0.66
    Hippo
    -0.65
    ⋘
    -0.65
     packet
    -0.65
    POSITIVE LOGITS
    Scanner
    3.53
     Scanner
    3.28
     scanner
    2.67
     scanners
    2.19
    scanner
    2.06
    BufferedReader
    1.78
     scanning
    1.59
     scan
    1.56
     Scan
    1.52
    SCAN
    1.48
    Activations Density 0.020%

    No Known Activations