© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9099
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find numerical expressions (digits, measurements, or numeric sequences).

    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
    로는
    0.74
     Businessman
    0.72
     basaltes
    0.70
     facere
    0.68
    ീ
    0.66
     exécut
    0.66
    ને
    0.64
    競争
    0.64
    این
    0.64
     lucru
    0.64
    POSITIVE LOGITS
    th
    0.71
    +
    0.63
     тя
    0.62
    ca
    0.60
     ত
    0.59
    றிந்த
    0.58
    ば
    0.58
    ij
    0.57
    훌
    0.56
    lica
    0.56
    Activations Density 0.020%

    No Known Activations