© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47636
    Prev
    Next
    INDEX
    Explanations

    code structure or testing contexts

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

    This neuron detects C# attribute declarations (the square-bracketed annotations like [TestFixture], [Category], [Preserve], etc.) in source code.

    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
     flux
    -0.80
     MARTIN
    -0.78
     conhe
    -0.77
     Lich
    -0.74
    堺
    -0.72
     Kung
    -0.72
     Whitman
    -0.71
     Flux
    -0.71
     Bing
    -0.70
    flux
    -0.70
    POSITIVE LOGITS
     NUnit
    0.93
     Grenada
    0.89
    SetUp
    0.85
    æng
    0.82
     Carrillo
    0.81
     Tulane
    0.81
     rectum
    0.80
    Opel
    0.78
    Castle
    0.78
     Kirchner
    0.78
    Activations Density 0.013%

    No Known Activations