© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10965
    Prev
    Next
    INDEX
    Explanations

    multiplication operations

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

    The neuron fires on numeric multiplication contexts—that is, numbers and words indicating multiplication or coefficients in calculation expressions.

    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_31_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
    -|
    0.55
     bát
    0.54
     disp
    0.52
     immisc
    0.52
     ulcers
    0.49
     Disp
    0.48
     hermit
    0.48
     dispensed
    0.48
    argmin
    0.48
    |-
    0.48
    POSITIVE LOGITS
     multiplied
    2.39
     multiplying
    2.19
    乘以
    2.16
     multiplies
    2.14
     multiplication
    2.13
     multiply
    2.09
    multiply
    2.03
    Multiply
    2.03
     Multiply
    1.96
     multiplicado
    1.92
    Activations Density 0.092%

    No Known Activations