© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113521
    Prev
    Next
    INDEX
    Explanations

    main method args

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

    the opening parenthesis and parameter list of method declarations in code, particularly activating strongly on the square brackets and "args" parameter in Java's main method signature.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     by
    -2.20
     was
    -1.98
     for
    -1.61
     becomes
    -1.59
     gets
    -1.57
    濬
    -1.54
    !)
    -1.52
     became
    -1.43
    燁
    -1.42
     if
    -1.41
    POSITIVE LOGITS
     uyt
    1.80
    こともあります
    1.73
     Achtung
    1.67
     onsdag
    1.63
    いいのか
    1.63
     lørdag
    1.63
    莛
    1.60
     Cedex
    1.58
    ING
    1.56
     hemel
    1.55
    Activations Density 0.008%

    No Known Activations