© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7088
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens, especially multi-digit and decimal numbers.

    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
    Integer
    0.45
    Msg
    0.45
    ->
    0.44
    ("
    0.42
    -\
    0.42
    MaxWidth
    0.42
    cInfo
    0.41
    x
    0.41
    Ди
    0.41
    ✘
    0.40
    POSITIVE LOGITS
     problém
    0.64
     procéd
    0.61
     prób
    0.59
     intrig
    0.57
     geopol
    0.56
     spéc
    0.55
     tariffs
    0.55
     dealings
    0.55
     preoccupation
    0.54
     strife
    0.54
    Activations Density 0.052%

    No Known Activations