© 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. 11878
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (especially multi‐digit numbers like years and other number strings).

    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
     імені
    0.59
     সেন্ট
    0.56
     სან
    0.55
     గుర్త
    0.54
     zakład
    0.54
     посетить
    0.54
     crescent
    0.53
    容
    0.53
     სპ
    0.52
     членов
    0.52
    POSITIVE LOGITS
     charts
    1.13
     chart
    1.09
     sales
    1.07
    Chart
    1.00
     Billboard
    1.00
     grosses
    0.98
    chart
    0.98
    Billboard
    0.97
     Chart
    0.94
     Charts
    0.90
    Activations Density 0.228%

    No Known Activations