© 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. 11650
    Prev
    Next
    INDEX
    Explanations

    are numerous, dominated, compatible

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

    That neuron fires on instances of the present‐tense plural copula “are.”

    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
     itself
    1.66
    是一个
    1.58
    是一個
    1.49
    它
    1.48
     isn
    1.35
     ہے
    1.26
     is
    1.24
     आहे
    1.22
    是个
    1.20
     它
    1.19
    POSITIVE LOGITS
     amelyek
    2.09
     которые
    2.08
     voltak
    2.05
     якія
    1.93
     რომლებიც
    1.93
     связанные
    1.85
     vannak
    1.81
     които
    1.80
     jotka
    1.80
     których
    1.74
    Activations Density 0.666%

    No Known Activations