© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11286
    Prev
    Next
    INDEX
    Explanations

    Foreign language/nationality descriptors

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

    The neuron is tuned to pick out numeric and quantitative expressions—counts, measurements, dates/times, percentages, and other number‐related tokens.

    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
     insofar
    0.77
     preventive
    0.73
     beforehand
    0.70
     and
    0.67
     afterward
    0.67
     similarly
    0.64
     adjuvant
    0.64
    ‒
    0.64
     fragments
    0.63
     curricula
    0.63
    POSITIVE LOGITS
     ঘোষনা
    1.03
    썻
    1.03
    非常的
    1.02
    凄い
    1.02
    出来る
    1.02
     наверное
    1.01
    ੳ
    1.01
     brasileiros
    0.98
    と言う
    0.97
     находиться
    0.95
    Activations Density 21.655%

    No Known Activations