© 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. 11508
    Prev
    Next
    INDEX
    Explanations

    SQL VALUES clauses and Node.js packages

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

    The neuron primarily detects numeric data tokens—especially floating‐point measurements and statistics.

    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
    ным
    0.78
    ς
    0.75
    ణి
    0.72
    ات
    0.72
    Current
    0.71
    Jenis
    0.70
    sı
    0.68
    CEA
    0.68
    없는
    0.68
    SRC
    0.67
    POSITIVE LOGITS
     Shirts
    0.77
    าะ
    0.73
    monium
    0.73
    🫧
    0.72
     ตั้ง
    0.71
     anhydrous
    0.71
     Soh
    0.71
    isetas
    0.70
    зульта
    0.70
     Excellence
    0.70
    Activations Density 0.000%

    No Known Activations