© 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. 86084
    Prev
    Next
    INDEX
    Explanations

    arithmetic and logical operators

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

    This neuron responds to operator symbols in code (e.g. bitwise, logical, arithmetic, and ternary operators).

    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
     メニュー
    -1.68
    
    -1.67
    The
    -1.64
     russia
    -1.58
    
    -1.48
    >#
    -1.41
     ()=>
    -1.40
     aldus
    -1.39
     "",
    -1.37
     '',
    -1.37
    POSITIVE LOGITS
     они
    1.70
     some
    1.64
     a
    1.63
     they
    1.56
     cintas
    1.55
     when
    1.50
     many
    1.49
     environments
    1.45
    了许多
    1.39
     using
    1.31
    Activations Density 0.029%

    No Known Activations