© 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. 127721
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    vább
    -1.20
     burbu
    -1.17
     piaci
    -1.16
    świet
    -1.14
     emblema
    -1.13
    ânsito
    -1.13
    ließen
    -1.12
     febrero
    -1.11
    гмента
    -1.11
     obiet
    -1.09
    POSITIVE LOGITS
    is
    1.54
    or
    1.53
    o
    1.48
    en
    1.44
    b
    1.42
    '
    1.42
    _
    1.40
    ur
    1.39
    io
    1.37
    he
    1.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.