© 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. 58168
    Prev
    Next
    INDEX
    Explanations

    foreign or specialized terms

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

    The neuron fires on content-bearing, descriptive words—especially technical or domain-specific nouns and adjectives—rather than on common function words.

    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
     they
    -1.78
    They
    -1.22
     was
    -1.16
    他们
    -1.14
     však
    -1.13
    $.
    -1.11
     persi
    -1.09
     být
    -1.09
    хіво
    -1.08
     profan
    -1.08
    POSITIVE LOGITS
     to
    1.69
    zzet
    1.52
     again
    1.48
     celles
    1.47
     kalend
    1.45
     DIFFERENT
    1.35
    dreamstime
    1.33
    Rozmiar
    1.33
    mohon
    1.33
    noah
    1.32
    Activations Density 0.220%

    No Known Activations