© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1750
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized in spotting numeric expressions (multi‐digit numbers, statistics, years, and other numeric data) in the text.

    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
     थोड़ा
    0.55
     podziel
    0.55
    第二
    0.54
     merak
    0.52
    textvariable
    0.51
    估
    0.51
     nantinya
    0.50
    owę
    0.50
    椂
    0.50
     khiển
    0.49
    POSITIVE LOGITS
     consecutive
    2.84
     Consecutive
    2.48
     consecutively
    2.42
    连续
    2.20
     consecut
    2.14
    連續
    2.13
     연속
    2.11
     consecutivos
    2.05
    連続
    2.03
     successive
    2.00
    Activations Density 0.367%

    No Known Activations