© 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. 8726
    Prev
    Next
    INDEX
    Explanations

    units of measurement (cm, kg, mol, m)

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

    The neuron activates on tokens representing scientific measurement units (especially mass, area, rate, and concentration units).

    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
    }{*}{
    0.66
     daisies
    0.65
    entos
    0.63
     olives
    0.62
    дцать
    0.62
    ä
    0.61
    ц
    0.59
     plums
    0.58
    τών
    0.58
    числи
    0.57
    POSITIVE LOGITS
    際に
    0.61
    Tem
    0.56
    %.
    0.55
    %。
    0.54
    쉬
    0.54
    বিনোদন
    0.53
     좋다
    0.53
     jederzeit
    0.52
     단순히
    0.52
    俣
    0.52
    Activations Density 0.004%

    No Known Activations