© 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. 24902
    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
     its
    -1.55
     any
    -1.50
     και
    -1.43
     oraz
    -1.38
     creating
    -1.28
     enhancing
    -1.28
     и
    -1.27
     by
    -1.26
     reducing
    -1.26
    createNewFile
    -1.25
    POSITIVE LOGITS
    </em>
    1.66
     Dinas
    1.45
    trying
    1.34
    
    1.33
    </b>
    1.29
    
    1.29
     actuellement
    1.28
    NOUN
    1.24
    despite
    1.23
    will
    1.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.