© 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. 75237
    Prev
    Next
    INDEX
    Explanations

    main method arguments

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

    The neuron fires on the Java main method’s parameter name “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_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
     its
    -1.28
    optarg
    -1.11
    Dě
    -1.11
     &___
    -1.09
    𝒃
    -1.08
     from
    -1.05
     prisonniers
    -1.05
     PUSTAKA
    -1.02
    原神
    -1.02
     permitió
    -1.02
    POSITIVE LOGITS
    0
    1.41
    \
    1.26
    ↵↵
    1.23
    2
    1.22
    habited
    1.13
    ,
    1.09
     according
    1.05
    ?
    1.05
    consola
    1.03
    5
    1.03
    Activations Density 0.001%

    No Known Activations