© 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. 7342
    Prev
    Next
    INDEX
    Explanations

    warm up, Interested in

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

    The neuron activates on numeric tokens, especially multi-digit numbers and decimals.

    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
     повышен
    0.77
    i
    0.77
     रवाना
    0.75
     staw
    0.70
    टा
    0.69
     রুম
    0.69
    ة
    0.69
     Ц
    0.69
    driving
    0.69
    humidity
    0.68
    POSITIVE LOGITS
     ambit
    0.80
    午前
    0.80
    edio
    0.76
     protons
    0.75
     metaphysics
    0.75
    EDITORIAL
    0.74
    꾿
    0.73
     tari
    0.73
     amino
    0.72
     blogs
    0.72
    Activations Density 0.000%

    No Known Activations