© 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. 10-GEMMASCOPE-RES-131K
    7. 45130
    Prev
    Next
    INDEX
    Explanations

    C# event handler sender

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

    The neuron fires on occurrences of typical event‐handler parameter names (e.g. “sender” and “e”), i.e. it detects event-handler method signatures or invocations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.64
     their
    -1.60
    !),
    -1.55
     our
    -1.52
     olisi
    -1.46
     be
    -1.43
     dubbed
    -1.43
     ardından
    -1.36
    …).
    -1.34
     meras
    -1.34
    POSITIVE LOGITS
    ↵↵
    1.68
    0
    1.63
    5
    1.55
    黽
    1.45
    8
    1.42
    這個
    1.40
    .
    1.37
    The
    1.36
    一樣
    1.34
    我們
    1.33
    Activations Density 0.007%

    No Known Activations