© 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. 8843
    Prev
    Next
    INDEX
    Explanations

    one element

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

    The neuron fires on phrases that specify a count or list of components—especially “consists/consisting of [number] [items/elements].”

    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
     сердце
    0.73
     Москва
    0.62
     اولین
    0.62
     верх
    0.60
    ricamente
    0.59
    ቑ
    0.59
     वी
    0.58
    √(
    0.58
     серд
    0.58
    cstdlib
    0.58
    POSITIVE LOGITS
     solitary
    0.58
     two
    0.57
     brief
    0.56
     ,
    0.55
     three
    0.55
     single
    0.55
    ↵
    0.54
     lone
    0.54
     monos
    0.54
    とともに
    0.54
    Activations Density 0.000%

    No Known Activations