© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14573
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to numeric tokens representing decimal or floating-point numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    સ્યા
    0.88
    Seventh
    0.83
    urètre
    0.82
    onomic
    0.79
    ઔ
    0.75
    BAN
    0.71
    ंगन
    0.71
    framework
    0.70
    forbidden
    0.70
    pathi
    0.70
    POSITIVE LOGITS
     (?)
    0.80
     (
    0.78
     IO
    0.78
    いた
    0.75
    0.75
     Esquire
    0.74
     Esports
    0.73
     -
    0.73
     👍
    0.73
     portare
    0.70
    Activations Density 0.000%

    No Known Activations