© 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. 128911
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

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

    The neuron is spotting places where event‐handler registrations occur (e.g. addEventListener or jQuery .on/ready/click bindings).

    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
     to
    -2.08
      
    -1.69
     обладает
    -1.62
    ons
    -1.59
    迨
    -1.57
    up
    -1.55
    倘
    -1.48
    us
    -1.45
    那时
    -1.44
    sp
    -1.42
    POSITIVE LOGITS
    voyez
    1.69
     aktivitet
    1.63
    咘
    1.58
     laiton
    1.55
    wachen
    1.50
    umuz
    1.49
     aimez
    1.48
     holz
    1.47
     wußte
    1.43
     經典
    1.43
    Activations Density 0.001%

    No Known Activations