© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12139
    Prev
    Next
    INDEX
    Explanations

    scientific or technical Q&A

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

    This neuron is tuned to pick up C-style code statements—especially C# “using …;” import directives (marked by the “using” keyword and trailing semicolon).

    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
     Objec
    -0.86
    potion
    -0.81
     dissipation
    -0.79
     щен
    -0.75
     Cypri
    -0.74
     Windy
    -0.74
     Clim
    -0.73
     fibroblast
    -0.73
     reseller
    -0.72
    励
    -0.72
    POSITIVE LOGITS
    datab
    0.90
    tired
    0.86
    important
    0.83
    orty
    0.82
    ghijkl
    0.82
    可惜
    0.79
    енная
    0.78
    several
    0.77
     sano
    0.77
    película
    0.77
    Activations Density 0.009%

    No Known Activations