© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58114
    Prev
    Next
    INDEX
    Explanations

    arithmetic and logical operators

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

    This neuron detects mentions of bitwise and logical operator symbols or names (e.g. ~, &, |, ^, &&, ||, “bitwise operators,” etc.) in code or technical discussion.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ða
    -0.71
    ią
    -0.70
    скому
    -0.65
     angek
    -0.65
    外線
    -0.63
    判定
    -0.63
     Tum
    -0.63
     fired
    -0.63
     Greg
    -0.62
     мог
    -0.62
    POSITIVE LOGITS
     operators
    1.59
     operator
    1.55
     Operator
    1.52
     Operators
    1.45
    Operator
    1.41
    operators
    1.30
    operator
    1.26
    Operators
    1.23
     OPERATOR
    1.02
    sizeof
    1.01
    Activations Density 0.050%

    No Known Activations