© 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. 83850
    Prev
    Next
    INDEX
    Explanations

    Java System.out or System.in

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

    The neuron fires strongly on the Java “System” token (e.g. System.in, System.out, System.err), i.e. it detects uses of the Java System I/O API.

    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
     those
    -0.90
    饑
    -0.88
     steadily
    -0.81
     within
    -0.80
     sviluppo
    -0.75
    站
    -0.74
     wolle
    -0.73
     みた
    -0.73
     acknowledged
    -0.73
     {'
    -0.73
    POSITIVE LOGITS
     out
    1.57
    out
    1.28
    OUT
    1.04
     SYSTEM
    1.00
    System
    1.00
     sout
    0.96
     systeem
    0.95
    system
    0.94
    opp
    0.93
     syste
    0.90
    Activations Density 0.002%

    No Known Activations