© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7926
    Prev
    Next
    INDEX
    Explanations

    javascript libraries and languages

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

    The neuron activates on JavaScript library or module names (e.g. “jquery,” “knockout,” “require”) in file‐path contexts.

    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
    ;;)
    0.47
     Quân
    0.45
    ب
    0.44
     želite
    0.43
     ristorante
    0.42
    گار
    0.41
     İstifadə
    0.40
    );//
    0.40
    厩
    0.40
    あなたが
    0.40
    POSITIVE LOGITS
    ENE
    0.48
    INE
    0.46
    sman
    0.45
    ributing
    0.45
    മായും
    0.42
    дные
    0.41
    ྗ
    0.40
    INI
    0.39
    nements
    0.39
     যাদ
    0.39
    Activations Density 0.000%

    No Known Activations