© 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. 6489
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on numeric tokens—quantities, measurements, and digit 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
    मतौर
    0.66
     ஆகிய
    0.66
    萆
    0.66
    ualaikum
    0.63
     सम्मिल
    0.63
     asalamualaikum
    0.63
     बनाएं
    0.62
    രീക്ഷ
    0.62
     Elig
    0.61
     ஆகியவை
    0.61
    POSITIVE LOGITS
    数を
    1.31
    数は
    1.28
    数の
    1.06
    數
    1.05
     count
    1.05
    数が
    1.03
    数的
    1.02
     எண்ணிக்க
    1.01
     sayısı
    1.00
    数为
    1.00
    Activations Density 0.587%

    No Known Activations