© 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. 98856
    Prev
    Next
    INDEX
    Explanations

    size descriptors followed by nouns

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

    The neuron activates on decimal-formatted numbers (i.e. floating-point measurements or quantities) in the text.

    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
     is
    -2.83
     of
    -2.66
     a
    -1.84
     one
    -1.77
     its
    -1.68
     all
    -1.66
     if
    -1.61
     in
    -1.61
     an
    -1.59
     \
    -1.57
    POSITIVE LOGITS
     colecciones
    2.25
    pulseira
    2.09
     envíos
    2.08
     préstamos
    2.05
     большие
    2.02
     contenedores
    2.02
     rebajas
    1.87
     uñas
    1.87
    pentru
    1.85
     producciones
    1.83
    Activations Density 0.204%

    No Known Activations