© 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. 7817
    Prev
    Next
    INDEX
    Explanations

    numbers in different languages

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

    The neuron specializes in detecting numerical tokens (numbers and numeric values, including years and decimal quantities).

    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
     ISR
    0.71
     Му
    0.70
    又は
    0.68
     Vanuatu
    0.68
     serta
    0.67
    驃
    0.66
     ม
    0.66
     Ра
    0.66
     विद्या
    0.65
     Prä
    0.64
    POSITIVE LOGITS
     reimag
    0.69
     famously
    0.64
    他和
    0.64
     svoj
    0.63
     तत्कालीन
    0.61
     damning
    0.59
    原本
    0.57
     единственный
    0.57
     কেবল
    0.57
    镜头
    0.56
    Activations Density 0.760%

    No Known Activations