© 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. 127716
    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
     rescate
    -1.14
     hermé
    -1.10
     biela
    -1.05
     détru
    -1.02
     bolí
    -1.02
     laiton
    -1.01
    垚
    -1.01
     étrang
    -1.01
     malheure
    -0.99
    Xuất
    -0.99
    POSITIVE LOGITS
    3
    1.20
    k
    1.09
    5
    1.07
    h
    1.05
    G
    1.04
    4
    1.04
    we
    1.03
    C
    1.02
    0
    0.99
    2
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.