© 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. 21469
    Prev
    Next
    INDEX
    Explanations

    DOM event target property access

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

    This neuron fires on occurrences of “target” (e.g. event.target or currentTarget property accesses) in 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_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
     its
    -1.69
     our
    -1.64
     июня
    -1.55
    元々
    -1.52
    と言われて
    -1.49
    even
    -1.45
    </sup>
    -1.38
     even
    -1.34
    就这样
    -1.26
     ミルク
    -1.23
    POSITIVE LOGITS
     máte
    1.62
     รวม
    1.58
     byste
    1.52
     tenemos
    1.52
    cómo
    1.50
     Atención
    1.48
     órg
    1.45
    लिखित
    1.45
     habt
    1.44
    alquiler
    1.44
    Activations Density 0.003%

    No Known Activations