© 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. 14041
    Prev
    Next
    INDEX
    Explanations

    answers and provides

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

    The neuron activates on numeric expressions—tokens containing numbers (e.g. percentages, decimals, counts).

    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
    십시오
    0.84
    ।'
    0.83
    ।
    0.81
    伨
    0.81
    ।।
    0.80
    '।
    0.76
     Кы
    0.75
    Су
    0.73
     EntityManager
    0.73
    ܸ
    0.72
    POSITIVE LOGITS
    0
    0.68
     globe
    0.61
    io
    0.61
     P
    0.57
     Group
    0.57
    phine
    0.57
    ida
    0.56
     de
    0.55
    ordination
    0.55
    нон
    0.55
    Activations Density 1.857%

    No Known Activations