© 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. 103642
    Prev
    Next
    INDEX
    Explanations

    object, struct, contract definitions

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

    the keyword "object" in programming code, particularly in object-oriented languages like Scala, Java, C++, and Solidity.

    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
    
    -2.16
    皤
    -1.95
    ༀ
    -1.91
    蛱
    -1.80
    薆
    -1.79
    鈊
    -1.78
    唖
    -1.73
    渽
    -1.72
    觏
    -1.71
    髡
    -1.69
    POSITIVE LOGITS
     are
    1.95
    ,
    1.89
     Regarding
    1.71
     Thus
    1.69
     Additionally
    1.64
     Furthermore
    1.64
     Important
    1.62
     Primarily
    1.53
     Historically
    1.53
     Comparing
    1.53
    Activations Density 0.008%

    No Known Activations