© 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. 99160
    Prev
    Next
    INDEX
    Explanations

    window scroll and resize events

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

    This neuron spotlights JavaScript code checking scroll (and resize) positions against numeric pixel values.

    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
     Organisator
    -1.54
    Retour
    -1.48
     Gastgeber
    -1.38
    Etape
    -1.35
    gebracht
    -1.34
    etcode
    -1.32
     bija
    -1.31
    יבור
    -1.30
    Jeu
    -1.28
     eſt
    -1.27
    POSITIVE LOGITS
     its
    1.68
     The
    1.50
     on
    1.48
     through
    1.38
     can
    1.36
    [
    1.33
     Other
    1.33
     importante
    1.27
     Our
    1.26
    B
    1.24
    Activations Density 0.114%

    No Known Activations