© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32695
    Prev
    Next
    INDEX
    Explanations

    verbs indicating state or status

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

    The neuron fires on copular verbs (forms of “to be” like “is” and “was”) in narrative statements.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     that
    -1.63
     we
    -1.57
     our
    -1.54
     I
    -1.53
     stated
    -1.52
     its
    -1.33
     you
    -1.24
    hålla
    -1.23
     Our
    -1.16
    iddish
    -1.16
    POSITIVE LOGITS
     "
    1.53
    hopped
    1.38
    estima
    1.21
     usw
    1.17
     \"
    1.14
     опубли
    1.14
     pihaknya
    1.13
    geries
    1.13
     hommage
    1.13
     topl
    1.13
    Activations Density 0.031%

    No Known Activations