© 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. 6451
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens—especially floating‐point numbers or measurements (decimal values) 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
    𝗲
    0.66
    と
    0.65
     ও
    0.63
    とか
    0.62
    性と
    0.61
    𝘆
    0.61
    とその
    0.60
    𝘦
    0.60
     এবং
    0.59
     و
    0.59
    POSITIVE LOGITS
     ones
    0.69
     others
    0.55
    വൃത്തി
    0.55
     respectively
    0.54
     Página
    0.53
     จังหวัด
    0.53
     equally
    0.52
     Carolina
    0.52
     trang
    0.50
     Consequently
    0.50
    Activations Density 1.324%

    No Known Activations