© 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. 14054
    Prev
    Next
    INDEX
    Explanations

    options and suggestions

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

    The neuron primarily detects numeric tokens—especially measurements, quantities, and decimal numbers.

    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
    رات
    0.92
    رض
    0.80
    rino
    0.76
    inação
    0.75
    Digite
    0.74
    Hrsg
    0.74
    畬
    0.73
    多数
    0.72
     gerek
    0.71
    ائمة
    0.71
    POSITIVE LOGITS
     WITHOUT
    0.76
    Alic
    0.75
     alliances
    0.74
     offering
    0.73
     bunnies
    0.73
     значительно
    0.72
     artworks
    0.70
     tablespoons
    0.70
    োদ
    0.69
     ARTICLES
    0.68
    Activations Density 0.000%

    No Known Activations