© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
    llten
    -1.83
     anything
    -1.78
     any
    -1.55
     quería
    -1.51
     querían
    -1.48
     pareció
    -1.45
     recordó
    -1.41
     añadió
    -1.41
     something
    -1.39
     habló
    -1.39
    POSITIVE LOGITS
     ihre
    1.48
     by
    1.44
    께
    1.42
     vaqueros
    1.41
    dees
    1.36
    setts
    1.30
     разные
    1.29
    mmä
    1.28
    дор
    1.27
     امروز
    1.27
    Activations Density 0.065%

    No Known Activations