© 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. 10-GEMMASCOPE-RES-131K
    7. 15679
    Prev
    Next
    INDEX
    Explanations

    extent or degree

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

    The neuron strongly activates on third‐person singular verbs ending in “-ates.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    どうも
    -1.42
     extremely
    -1.41
    皆さん
    -1.40
    ,
    -1.40
    女優
    -1.39
    tawesome
    -1.38
     другую
    -1.35
    とても
    -1.35
     somewhat
    -1.34
     “
    -1.34
    POSITIVE LOGITS
     its
    2.22
     this
    2.06
     these
    2.00
     from
    1.79
     each
    1.77
     poszczegól
    1.66
     those
    1.66
     various
    1.63
     now
    1.59
     as
    1.50
    Activations Density 0.056%

    No Known Activations