© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13752
    Prev
    Next
    INDEX
    Explanations

    airport transfer

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

    The neuron specifically responds to numerical expressions—numbers, ages, fees, and other digit‐based tokens—typically found in transfer and loan announcement contexts.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    球队
    0.73
     Mannschaften
    0.68
     Mannschaft
    0.66
     stadion
    0.64
     ikon
    0.63
    Messi
    0.63
     జట్టు
    0.62
     турни
    0.61
     팀
    0.60
     memainkan
    0.60
    POSITIVE LOGITS
     transfer
    1.36
     Transfer
    1.26
    transfer
    1.23
    Transfer
    1.21
     transfers
    1.20
     transferring
    1.08
     transferred
    1.07
     TRANSFER
    1.05
     Transfers
    1.02
     transfert
    1.02
    Activations Density 0.103%

    No Known Activations