© 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. 58228
    Prev
    Next
    INDEX
    Explanations

    names and movie titles

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

    The neuron strongly activates on capitalized proper nouns—especially personal names (e.g. directors, authors) and titles of films or books.

    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
    on
    -1.78
    atórios
    -1.68
    {
    -1.44
    像是
    -1.37
    JAV
    -1.36
    PICTOGRAM
    -1.35
    是一种
    -1.32
    袮
    -1.32
    ࿊
    -1.32
    eterangan
    -1.30
    POSITIVE LOGITS
     erfolgreichen
    1.57
    mathrm
    1.49
     localizada
    1.39
     борьбе
    1.34
    缟
    1.31
    ‘
    1.30
     sicheren
    1.30
    people
    1.27
     великолеп
    1.27
     bombilla
    1.27
    Activations Density 0.008%

    No Known Activations