© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9296
    Prev
    Next
    INDEX
    Explanations

    population counts and statistics

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

    This neuron responds to numeric tokens—especially patent claim numbers, numerical measurements, and decimal values.

    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_31_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
    埸
    0.72
    従来
    0.71
    晤
    0.69
    全く
    0.66
    従来の
    0.65
     unduly
    0.64
     hitherto
    0.60
     defray
    0.60
    镞
    0.59
     radically
    0.59
    POSITIVE LOGITS
     вашей
    0.73
     LiDAR
    0.70
     метров
    0.66
     synced
    0.65
     인천
    0.64
     vuông
    0.64
     иннова
    0.63
     Bengaluru
    0.62
     እና
    0.61
     suelo
    0.61
    Activations Density 0.041%

    No Known Activations