© 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. 34-GEMMASCOPE-RES-131K
    7. 32224
    Prev
    Next
    INDEX
    Explanations

    awk commands and programming constructs

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

    This neuron fires on occurrences of the awk command (the literal "awk") in code or shell-pipeline contexts.

    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
    kwds
    -0.78
    TLC
    -0.73
    開封
    -0.72
    Tess
    -0.72
     eup
    -0.72
    水着
    -0.71
    Returned
    -0.71
    扦
    -0.71
     популяр
    -0.70
     Sada
    -0.70
    POSITIVE LOGITS
    NF
    1.25
    BEGIN
    1.18
     NF
    1.15
     FS
    1.09
    ORS
    1.07
    OF
    1.06
    FS
    1.02
    gsub
    0.98
     NR
    0.98
     gens
    0.96
    Activations Density 0.040%

    No Known Activations