© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130051
    Prev
    Next
    INDEX
    Explanations

    This neuron identifies C# code, especially type names and identifiers in method declarations and parameter lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code keywords and calls

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ଂ
    -1.52
    Fakta
    -1.49
     pfalz
    -1.48
     السياس
    -1.48
    rrggbb
    -1.45
     matchs
    -1.44
     abbildung
    -1.42
    皤
    -1.40
    ÈNE
    -1.40
    vedades
    -1.39
    POSITIVE LOGITS
     this
    1.61
     being
    1.45
     active
    1.40
     actively
    1.40
     will
    1.36
     he
    1.32
     out
    1.32
    𝑞
    1.30
    ७
    1.29
     game
    1.28
    Activations Density 0.003%

    No Known Activations