© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6429
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to numeric tokens (digits, percentages, and other quantities) 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_24_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
    /
    1.46
     (
    1.14
     &
    1.13
     /
    1.11
    (
    1.11
     +
    0.99
    +
    0.95
     utilizes
    0.94
     içerisinde
    0.93
     R
    0.91
    POSITIVE LOGITS
    Reuters
    1.39
     Reuters
    1.31
     Xinhua
    1.22
     lawmaker
    1.17
     AFP
    1.14
     বুধবার
    1.12
    AFP
    1.12
    官员
    1.11
     শুক্রবার
    1.10
     দেশটির
    1.10
    Activations Density 0.429%

    No Known Activations