© 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. 15925
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and code segments

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

    The neuron strongly activates on numerical tokens (quantities, measurements, IDs, codes, etc.).

    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
     základě
    0.76
    ครื่อง
    0.64
    มาตรฐาน
    0.64
    了一個
    0.61
    舖
    0.61
    ன்மை
    0.60
    ాత్ర
    0.58
     τρόπο
    0.57
    ärt
    0.57
    逺
    0.56
    POSITIVE LOGITS
    uwen
    0.66
    ected
    0.65
     Kalyan
    0.60
     Advertisement
    0.59
     Vial
    0.57
    eldorf
    0.56
     Reinforced
    0.55
     Pic
    0.54
    ftop
    0.54
    ellular
    0.54
    Activations Density 1.259%

    No Known Activations