© 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. 34-GEMMASCOPE-RES-131K
    7. 93922
    Prev
    Next
    INDEX
    Explanations

    programming code and configuration

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

    This neuron activates on programming‐language tokens—identifiers, symbols, and code constructs.

    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
    nefs
    -0.83
    емом
    -0.81
    ũ
    -0.79
    Treasurer
    -0.79
     Soud
    -0.76
    seling
    -0.76
     marzo
    -0.75
    鎊
    -0.75
    ỏa
    -0.75
    nościo
    -0.75
    POSITIVE LOGITS
    ultur
    0.78
     yetu
    0.77
     gestalten
    0.77
    Parsing
    0.77
     parsing
    0.76
     intrepid
    0.73
    組み立て
    0.73
     Culture
    0.73
    wh
    0.72
    Ili
    0.71
    Activations Density 0.001%

    No Known Activations