© 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. 64531
    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
     what
    -1.58
     chré
    -1.47
     about
    -1.40
    település
    -1.30
    包括
    -1.27
     people
    -1.27
     how
    -1.24
    に行きました
    -1.24
     religieuses
    -1.24
    áról
    -1.20
    POSITIVE LOGITS
     årets
    1.37
     onsdag
    1.34
     torsdag
    1.33
     protéines
    1.28
     fredag
    1.27
     eletrônico
    1.26
     SPAIN
    1.19
    хами
    1.18
     તે
    1.17
     savu
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.