© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10048
    Prev
    Next
    INDEX
    Explanations

    remember conversions, percentages, numbers

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

    The neuron strongly activates on large numeric tokens—especially multi-digit decimal numbers (e.g. “2345.7549”).

    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
     beschäftigen
    0.54
     приходится
    0.54
    듭
    0.53
     يش
    0.53
     réel
    0.53
     کرنا
    0.52
     compagn
    0.49
    デュ
    0.49
     እንደሚ
    0.49
     né
    0.48
    POSITIVE LOGITS
    inam
    0.62
     Statistik
    0.58
    டையாக
    0.57
    juv
    0.57
     Unfall
    0.56
     DAMAGE
    0.55
    ﺻ
    0.54
    hik
    0.53
     социальных
    0.52
     disrespect
    0.52
    Activations Density 0.000%

    No Known Activations