© 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. 32666
    Prev
    Next
    INDEX
    Explanations

    like comparisons, analogies

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

    The neuron fires on major punctuation marks (periods, commas, semicolons) that mark sentence or clause boundaries.

    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
     especialmente
    -0.96
     errichtet
    -0.89
    ियन
    -0.88
     البحث
    -0.87
     zugelassen
    -0.86
     București
    -0.86
    particularly
    -0.85
     همچنین
    -0.85
     trên
    -0.85
     hierv
    -0.83
    POSITIVE LOGITS
     there
    1.02
     both
    1.02
     just
    0.99
    Both
    0.99
     wherein
    0.95
    Mst
    0.92
     where
    0.91
     can
    0.91
     сначала
    0.90
     líqu
    0.89
    Activations Density 0.022%

    No Known Activations