© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    start, first, beginning

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

    The neuron strongly activates on numeric expressions (digits, measurements, statistics, etc.), effectively detecting numbers and quantities in the text.

    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
    ات
    0.89
    في
    0.84
    thank
    0.81
     pigmentation
    0.79
    more
    0.78
    related
    0.77
    ك
    0.77
     Furthermore
    0.76
    꿋
    0.76
     همچنین
    0.76
    POSITIVE LOGITS
    先把
    1.18
     muốn
    1.13
     iemand
    1.05
     хоче
    1.05
    要
    1.03
    まずは
    1.00
     먼저
    0.98
    ต้องการ
    0.98
     хотим
    0.98
     まず
    0.97
    Activations Density 6.625%

    No Known Activations