© 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. 16468
    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
     this
    -1.47
     they
    -1.23
     which
    -1.19
    6
    -1.13
     these
    -1.10
    3
    -1.08
     had
    -1.05
     for
    -1.05
    5
    -1.05
     their
    -1.02
    POSITIVE LOGITS
    either
    1.13
    también
    1.12
     appliquer
    1.10
     minimalis
    1.09
    Также
    1.09
     faciliter
    1.08
     fous
    1.06
     berge
    1.06
    cabeza
    1.05
    همچنین
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.