© 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. 4816
    Prev
    Next
    INDEX
    Explanations

    kilogram, brand, ozone, N

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

    This neuron responds to numeric tokens—identifying numbers, dates, measurements, and statistics 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
     입니다
    0.90
    /
    0.80
     جدید
    0.77
     availability
    0.76
    입니다
    0.75
     মোঃ
    0.74
     unavailability
    0.73
    Ꮑ
    0.71
     ২০২৩
    0.70
     elevation
    0.70
    POSITIVE LOGITS
     paysans
    1.06
     warships
    1.06
     prostitutes
    1.02
     novelists
    0.98
     yachts
    0.96
     estadounidenses
    0.95
     ameryka
    0.94
     soldats
    0.93
     músicos
    0.93
     escritores
    0.92
    Activations Density 0.499%

    No Known Activations