© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on large numeric expressions (especially digits and commas) in formatted numbers.

    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
    ikos
    0.63
    iging
    0.63
    國家
    0.60
    〝
    0.60
    证券公司
    0.59
    raits
    0.59
    ማ
    0.59
    ু
    0.58
    iko
    0.56
    ق
    0.56
    POSITIVE LOGITS
     illetve
    1.10
     odnosno
    0.94
    ০০০
    0.92
     respectivamente
    0.86
     respectively
    0.78
     czyli
    0.77
     тобто
    0.76
     отличи
    0.71
     ovvero
    0.70
    ;,
    0.67
    Activations Density 0.137%

    No Known Activations