© 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. 2037
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens, especially decimal numbers and other numeric values.

    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
     নির্দিষ্ট
    0.50
    6
    0.48
     grits
    0.48
    7
    0.46
    8
    0.45
    0
    0.45
    utils
    0.44
    3
    0.44
    insight
    0.43
     разными
    0.42
    POSITIVE LOGITS
     Sikh
    0.63
     vocalist
    0.58
     cinque
    0.57
     numerose
    0.57
     Preschool
    0.55
     billionaire
    0.55
     midfielder
    0.54
     Biden
    0.54
     vendredi
    0.54
     আওয়ামী
    0.53
    Activations Density 0.288%

    No Known Activations