© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on tokens representing numeric values—numbers, percentages, or other quantitative amounts.

    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
    None
    0.57
    IEnumerable
    0.55
    ("",
    0.55
    几
    0.54
    низ
    0.53
    Array
    0.52
    几年
    0.52
    Alf
    0.50
    NONE
    0.50
    $>$
    0.50
    POSITIVE LOGITS
     sebanyak
    0.90
     whopping
    0.80
     approximately
    0.78
     $
    0.76
     około
    0.76
     sebesar
    0.75
     pukul
    0.75
     nearly
    0.74
     ‪
    0.74
     yaklaşık
    0.74
    Activations Density 0.706%

    No Known Activations