© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5649
    Prev
    Next
    INDEX
    Explanations

    `((` followed by programming identifiers

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

    This neuron fires on code arrow symbols (the “=>” in lambda/arrow function expressions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     시작하겠습니다
    0.54
    ochemistry
    0.48
     низкой
    0.47
    >[</
    0.46
     ambientales
    0.46
     하겠습니다
    0.45
    ete
    0.44
    '");
    0.44
    ounds
    0.43
     rectMode
    0.43
    POSITIVE LOGITS
     kişinin
    0.46
    accessor
    0.45
    GitHub
    0.44
    ки
    0.43
    navigationItem
    0.43
     rende
    0.43
    मानी
    0.43
    м
    0.43
    github
    0.42
    htaccess
    0.42
    Activations Density 0.000%

    No Known Activations