© 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. 6773
    Prev
    Next
    INDEX
    Explanations

    generics in code

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

    This neuron detects C# generic‐type declarations by spotting the angle‐bracketed type‐parameter syntax (e.g. “<TEntity, TDbConnection>”).

    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
     ки
    -0.82
     eventName
    -0.77
    íticos
    -0.73
    "$_
    -0.73
     confessed
    -0.72
     intValue
    -0.71
    ذلك
    -0.71
     instanceof
    -0.71
    movq
    -0.71
    寝
    -0.70
    POSITIVE LOGITS
    ätzen
    0.90
    کت
    0.85
     Vocals
    0.84
    Poco
    0.84
    ალ
    0.83
     propietarios
    0.80
     waarin
    0.79
     rebut
    0.79
    fiore
    0.78
    对待
    0.78
    Activations Density 0.014%

    No Known Activations