© 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. 10-GEMMASCOPE-RES-131K
    7. 11999
    Prev
    Next
    INDEX
    Explanations

    java code declarations

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

    the word "java" in import statements or code.

    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
     at
    -2.92
    u
    -2.84
     for
    -2.42
    uspiel
    -2.39
     any
    -2.34
     excessively
    -2.34
    n
    -2.28
     being
    -2.28
     the
    -2.16
     by
    -2.13
    POSITIVE LOGITS
     \
    3.02
    进入了
    2.59
    缑
    2.42
    雠
    2.23
    2
    2.16
    当场
    2.14
     PÅ
    2.09
    艄
    2.08
    
    2.03
    蕖
    1.99
    Activations Density 0.014%

    No Known Activations