© 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. 32928
    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
     all
    -1.41
     get
    -1.14
     on
    -1.12
     in
    -1.11
     both
    -1.09
     allow
    -1.03
     just
    -1.03
     That
    -1.01
     what
    -1.01
     (
    -1.00
    POSITIVE LOGITS
     magnificent
    1.32
     gigantic
    1.27
     astounding
    1.24
     overarching
    1.23
     unending
    1.22
    ܆
    1.21
     prosegu
    1.21
    another
    1.20
     breathtaking
    1.18
     wacky
    1.17
    Activations Density 0.000%

    No Known Activations