© 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. 34-GEMMASCOPE-RES-131K
    7. 106220
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -1.73
    死者
    -1.27
    Rptr
    -1.23
    providedIn
    -1.22
     all
    -1.15
    URDAY
    -1.14
     sillä
    -1.13
    他也
    -1.10
    TINGS
    -1.09
     get
    -1.08
    POSITIVE LOGITS
    
    1.17
     クルー
    1.16
     новую
    1.16
    ")]
    1.16
    Frage
    1.13
    Epil
    1.12
    achios
    1.12
     prospet
    1.09
    ワクワク
    1.09
     creat
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.