© 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. 12460
    Prev
    Next
    INDEX
    Explanations

    about repositories, KL, PDF, Market

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

    The neuron fires strongly on numeric tokens (quantities, years, measurements, and other 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
    מה
    0.61
     白色
    0.57
    主要的
    0.56
     коюм
    0.55
     为
    0.54
    顾客
    0.53
     其
    0.53
     程序
    0.53
     آیات
    0.52
     dưới
    0.52
    POSITIVE LOGITS
    こういう
    1.38
     подобных
    1.33
     இதுபோன்ற
    1.16
     подобные
    1.16
    このような
    1.09
     ഇത്തരം
    1.03
     एखा
    1.02
     organizations
    0.97
     takich
    0.96
     sociedades
    0.93
    Activations Density 0.368%

    No Known Activations