© 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. 22-GEMMASCOPE-RES-131K
    7. 38440
    Prev
    Next
    INDEX
    Explanations

    code statement terminators

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

    The neuron fires on code lines that import or include external modules or headers (e.g. “using …;” and “#include …”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     hieronder
    -0.88
     eignet
    -0.88
     &
    -0.87
     below
    -0.85
     efforts
    -0.84
     at
    -0.83
     frumos
    -0.82
     vinilo
    -0.81
     advice
    -0.81
    カツ
    -0.81
    POSITIVE LOGITS
     Eğer
    0.94
     Çünkü
    0.89
     MLA
    0.85
     bikers
    0.84
    était
    0.84
    Воспитатель
    0.83
     Simplemente
    0.83
     のか
    0.82
     wüns
    0.81
    dö
    0.81
    Activations Density 0.003%

    No Known Activations