© 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. 58102
    Prev
    Next
    INDEX
    Explanations

    cities and places

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

    The neuron strongly activates on multi‐word proper names and titles (e.g. movie titles, place names, monuments, or person names), i.e. named entities.

    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
     these
    -1.87
    这些
    -1.72
     orologio
    -1.71
     těchto
    -1.70
     különböző
    -1.70
    這些
    -1.66
     takich
    -1.63
    
    -1.63
    tauchen
    -1.62
    樒
    -1.55
    POSITIVE LOGITS
    </h3>
    1.52
    !
    1.47
     л
    1.39
    y
    1.37
     suporta
    1.28
     teste
    1.27
     élevées
    1.27
    Y
    1.24
    i
    1.24
     You
    1.20
    Activations Density 0.040%

    No Known Activations