© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    leave request

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

    The neuron fires on numerical measurement tokens—especially decimal or floating-point 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
    く
    0.81
    くい
    0.75
    性は
    0.75
    あった
    0.73
     instrumental
    0.73
     Peaks
    0.73
     Laplace
    0.73
    カス
    0.72
     Keystone
    0.71
     Titan
    0.71
    POSITIVE LOGITS
     výrob
    0.76
     isomorphisms
    0.73
    ב
    0.72
    Ela
    0.71
    Tienes
    0.71
     Среди
    0.70
    Kui
    0.68
    Applicant
    0.67
    ग्राहक
    0.66
    Укра
    0.66
    Activations Density 0.000%

    No Known Activations