© 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. 2851
    Prev
    Next
    INDEX
    Explanations

    environment and scope names

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

    The neuron fires on code identifiers (variable, function, and property names) rather than language keywords or punctuation.

    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
     atrás
    -0.87
     MSU
    -0.82
     antiquity
    -0.81
     гарни
    -0.77
    ApiOperation
    -0.76
    offie
    -0.71
    ksp
    -0.71
    Francia
    -0.71
    Perú
    -0.71
    وگرافی
    -0.69
    POSITIVE LOGITS
     environment
    1.79
     variables
    1.52
     locals
    1.42
     Environment
    1.38
    Environment
    1.37
    variables
    1.30
    Variables
    1.30
     environ
    1.27
    locals
    1.25
     globals
    1.25
    Activations Density 0.054%

    No Known Activations