© 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. 2966
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric expressions (e.g. numbers, ratios, timestamps) 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
    ห์
    0.95
    ได
    0.86
    ఋ
    0.86
     จึง
    0.84
     স্বয়ং
    0.82
     či
    0.82
     związ
    0.81
    উদাহরণ
    0.80
     เม
    0.80
    ษ
    0.79
    POSITIVE LOGITS
    enfants
    0.78
    拥
    0.77
    tocol
    0.76
    unjung
    0.75
    صل
    0.74
     femmes
    0.74
    tourism
    0.73
    奄
    0.71
    toBytes
    0.71
    ركة
    0.71
    Activations Density 0.181%

    No Known Activations