© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130449
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on ES6 import clauses, specifically on the “from” keyword and the default‐import identifiers in import statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    import from statements or namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     bara
    -1.08
     complet
    -1.03
     conno
    -0.98
     sincer
    -0.98
     march
    -0.97
     incess
    -0.94
    AGEM
    -0.94
    耙
    -0.94
     rute
    -0.93
    RESUM
    -0.92
    POSITIVE LOGITS
     kontaktu
    1.15
    ਫ਼
    1.05
     what
    1.03
     selepas
    1.03
     or
    0.98
     klienta
    0.97
    ָל
    0.95
     благодаря
    0.92
    Không
    0.91
     ||
    0.91
    Activations Density 0.001%

    No Known Activations