© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111788
    Prev
    Next
    INDEX
    Explanations

    main method String args

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

    the parameters of Java main method declarations, specifically "String[] args".

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

    The neuron strongly activates on the Java main‐method parameter declaration “String[] args.”

    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
    こんばん
    -1.87
     the
    -1.77
     your
    -1.73
    ༛
    -1.73
    良心
    -1.70
     when
    -1.61
    图片来源
    -1.59
     some
    -1.58
     various
    -1.57
     them
    -1.55
    POSITIVE LOGITS
    \
    1.98
    .
    1.98
    ↵↵
    1.90
     are
    1.89
    </em>
    1.73
    从来
    1.60
     汁
    1.60
    豬
    1.59
    巔
    1.53
    拚
    1.50
    Activations Density 0.004%

    No Known Activations