© 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. 38492
    Prev
    Next
    INDEX
    Explanations

    data, time, content, city, vertex

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

    The neuron highlights the main content-bearing nouns or topic words in each passage.

    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
     you
    -1.95
     also
    -1.77
     your
    -1.68
     such
    -1.62
     an
    -1.59
     using
    -1.51
     of
    -1.50
     and
    -1.45
     their
    -1.45
     like
    -1.45
    POSITIVE LOGITS
     ۸
    1.72
     marte
    1.69
     pietre
    1.63
    annique
    1.63
     pérd
    1.59
     ۱۲
    1.59
     vinil
    1.59
     banane
    1.59
     conster
    1.55
     fré
    1.52
    Activations Density 0.067%

    No Known Activations