© 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. 74000
    Prev
    Next
    INDEX
    Explanations

    java programming language

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

    The neuron flags occurrences of the substring “java” (i.e. references to Java in code, imports, package names, file paths, etc.).

    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
    '
    -2.73
    ↵
    -2.67
    凄い
    -2.30
    
    -2.23
    u
    -2.20
     “
    -2.19
    他们的
    -2.17
     ricas
    -2.16
    柺
    -2.16
    汌
    -2.14
    POSITIVE LOGITS
    In
    3.19
    裢
    2.66
    The
    2.64
    ции
    2.63
    ፔ
    2.58
     手绘
    2.50
    Surprisingly
    2.45
    
    2.39
    Since
    2.39
    If
    2.39
    Activations Density 0.021%

    No Known Activations