© 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. 5358
    Prev
    Next
    INDEX
    Explanations

    and

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects numeric expressions such as dates, times, and other number tokens.

    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
     maupun
    1.77
     lẫn
    1.45
    及
    1.16
     illetve
    1.15
     سمیت
    1.08
     एवं
    1.07
     sowie
    1.07
     सहित
    1.07
     sekä
    1.06
     ataupun
    1.04
    POSITIVE LOGITS
     ហើយ
    1.80
    并
    1.77
    并在
    1.76
    并且
    1.74
    并将
    1.74
     并
    1.73
     거고
    1.70
    었고
    1.63
    했고
    1.60
    並且
    1.57
    Activations Density 0.744%

    No Known Activations