© 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. 22-GEMMASCOPE-RES-131K
    7. 67796
    Prev
    Next
    INDEX
    Explanations

    `args` in program arguments

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

    The neuron fires on the “args” identifier in method parameter lists (e.g. the command‐line arguments variable in a Java/C# main signature).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    祇
    -1.20
     its
    -1.05
    <tfoot>
    -1.04
    耘
    -1.02
     decorada
    -1.00
    ✎
    -0.97
    entet
    -0.93
    ющему
    -0.93
    RICULUM
    -0.93
    вная
    -0.93
    POSITIVE LOGITS
    0
    1.07
     インチ
    0.98
     paragon
    0.96
    的爱
    0.93
    她們
    0.93
    roughts
    0.92
    分鐘
    0.91
    マジで
    0.91
     Schmerzen
    0.90
     récla
    0.90
    Activations Density 0.001%

    No Known Activations