© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 436
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on various inflections of the verb “to be” (is, are, be, ’m, ’re, etc.).

    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
    when
    0.29
     quando
    0.29
     When
    0.28
    lucent
    0.27
    which
    0.27
     when
    0.27
     which
    0.26
     ,
    0.26
     But
    0.25
     That
    0.25
    POSITIVE LOGITS
     getting
    0.68
     experiencing
    0.67
     exerting
    0.64
     behaving
    0.64
     taking
    0.63
     undergoing
    0.63
     benefiting
    0.63
     trying
    0.62
     đang
    0.61
     attempting
    0.61
    Activations Density 1.447%

    No Known Activations