© 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. 22461
    Prev
    Next
    INDEX
    Explanations

    javascript find method

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

    The neuron fires on occurrences of the method name “find” (e.g. jQuery’s .find calls).

    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
     not
    -2.03
     on
    -1.90
     because
    -1.76
     use
    -1.71
     in
    -1.71
     if
    -1.42
     particularly
    -1.42
     or
    -1.42
     when
    -1.42
     especially
    -1.40
    POSITIVE LOGITS
     garant
    1.61
     Perſ
    1.57
    ޏ
    1.43
     mettent
    1.43
     possono
    1.42
    쨩
    1.35
    好看的
    1.30
     possano
    1.29
     inade
    1.28
     ‚
    1.28
    Activations Density 0.011%

    No Known Activations