© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39655
    Prev
    Next
    INDEX
    Explanations

    main method

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

    The neuron responds to code lines that introduce or begin function definitions—especially the “main(…)” signature and its ensuing block.

    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
    czegóły
    -0.95
    Ql
    -0.94
    OrNil
    -0.88
     ventas
    -0.87
    唁
    -0.86
     amable
    -0.85
     bailando
    -0.85
    nitř
    -0.85
     删除
    -0.84
    انگلیسی
    -0.83
    POSITIVE LOGITS
    鮑
    0.90
     kuf
    0.84
    RY
    0.83
     tenda
    0.83
     example
    0.81
     uncin
    0.80
    veras
    0.80
    ZipCode
    0.79
     prossima
    0.78
     instance
    0.77
    Activations Density 0.002%

    No Known Activations