© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111417
    Prev
    Next
    INDEX
    Explanations

    event handler parameters (sender, e)

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

    the pattern "object sender," which is a standard C# event handler parameter signature.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     "
    -1.71
     then
    -1.46
    了些
    -1.42
     $
    -1.41
    o
    -1.41
    ve
    -1.38
    end
    -1.38
    $
    -1.36
    y
    -1.35
    second
    -1.34
    POSITIVE LOGITS
    pulsera
    1.71
     शुर
    1.65
    colgante
    1.55
    بالإنجليزية
    1.54
    These
    1.52
     Jeden
    1.49
    riterien
    1.48
    ࿚
    1.48
    Добавлено
    1.48
     regarding
    1.48
    Activations Density 0.002%

    No Known Activations