© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41345
    Prev
    Next
    INDEX
    Explanations

    javascript code block termination

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

    This neuron detects the closing brace-and-parenthesis sequence (e.g. “});”) that ends JavaScript/jQuery callback or code‐block definitions.

    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
    ⢕
    -1.64
    Jueves
    -1.62
     samtidig
    -1.58
    ጓ
    -1.56
     menggunakan
    -1.55
     utilizar
    -1.55
     استفاده
    -1.55
     facendo
    -1.51
    ﻦ
    -1.51
    ไม่มี
    -1.47
    POSITIVE LOGITS
    k
    2.33
    :
    2.20
    ;
    2.19
    );
    1.77
    c
    1.67
    ?
    1.60
     of
    1.59
    l
    1.58
    >
    1.58
     ”
    1.56
    Activations Density 0.011%

    No Known Activations