© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4257
    Prev
    Next
    INDEX
    Explanations

    generate, retrieve, sourcing

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

    The main thing this neuron does is detect numeric expressions (quantities, measurements, statistics, or other 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
    ೋಜನ
    0.71
    Clazz
    0.69
     Балтбет
    0.65
    焔
    0.64
     Возможно
    0.63
    ElementName
    0.63
     OBJECTTYPE
    0.63
    ♨
    0.63
    ایا
    0.62
    Есть
    0.62
    POSITIVE LOGITS
     and
    0.73
     or
    0.73
     lithium
    0.71
     proteins
    0.69
     patents
    0.68
     minerals
    0.65
     wetlands
    0.65
     opioids
    0.65
     primates
    0.64
     nematodes
    0.63
    Activations Density 0.338%

    No Known Activations