© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    amounts of money

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

    This neuron activates on numeric expressions—especially large quantities and monetary figures (e.g., “million,” decimal numbers, and similar numerals).

    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
     mmol
    0.93
    ET
    0.85
     mei
    0.84
    ่
    0.84
    MktCap
    0.83
     распоря
    0.80
     posti
    0.79
    StaffID
    0.79
    ERON
    0.78
     begitu
    0.77
    POSITIVE LOGITS
    疾病
    0.87
    nings
    0.84
    වත්
    0.80
    ність
    0.80
    的作用
    0.79
    各地
    0.78
    
    0.77
    作用
    0.76
    wirkung
    0.75
    上半年
    0.75
    Activations Density 0.024%

    No Known Activations