© 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. 68590
    Prev
    Next
    INDEX
    Explanations

    all of which

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

    The neuron strongly activates on the word “all,” identifying that specific quantifier.

    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
     would
    -2.20
     is
    -2.09
     what
    -2.02
     will
    -1.98
     all
    -1.97
     has
    -1.94
     as
    -1.93
     cannot
    -1.93
    4
    -1.91
     how
    -1.86
    POSITIVE LOGITS
    哙
    1.84
    茔
    1.82
     rivi
    1.79
     espé
    1.75
    釔
    1.74
     الأحمر
    1.69
    旁边的
    1.69
     světa
    1.68
    луйста
    1.66
     maniere
    1.66
    Activations Density 0.029%

    No Known Activations