© 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. 64571
    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
    Not in Any Lists

    No Comments

    Negative Logits
     vinyle
    -1.31
     diamant
    -1.22
     restaura
    -1.18
     ajustable
    -1.17
     servis
    -1.16
    Their
    -1.13
     guir
    -1.13
     cabine
    -1.12
    iedział
    -1.09
     broche
    -1.08
    POSITIVE LOGITS
     vych
    0.99
     pojawia
    0.99
     ám
    0.98
    &
    0.95
    _
    0.94
    了些
    0.93
     vigencia
    0.91
    ichert
    0.90
    ul
    0.90
     více
    0.90
    Activations Density 0.000%

    No Known Activations