© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11380
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and numbers

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

    This neuron detects arithmetic or numerical operation terms and expressions (e.g., division, multiplication, odd/even, increasing).

    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
     بدأ
    0.91
    📨
    0.90
     时尚
    0.84
     技術
    0.82
    研修
    0.81
    Gestion
    0.81
    审批
    0.81
     بشأن
    0.80
    📲
    0.80
     обучения
    0.80
    POSITIVE LOGITS
     integers
    1.15
     divisors
    1.13
     integer
    1.09
     multiples
    1.06
     polynomials
    1.05
     divisible
    1.05
     monomials
    1.04
     permutations
    1.00
     molecular
    0.99
     denominators
    0.98
    Activations Density 0.414%

    No Known Activations