© 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. 127788
    Prev
    Next
    INDEX
    Explanations

    located in or at

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     During
    -1.55
     may
    -1.52
     That
    -1.48
     Even
    -1.48
     With
    -1.48
     Perhaps
    -1.47
     that
    -1.46
     allow
    -1.45
     in
    -1.45
     could
    -1.43
    POSITIVE LOGITS
     corriger
    1.59
     fidé
    1.55
     trésor
    1.53
     compagnon
    1.53
     patro
    1.49
     réfrig
    1.49
     intensif
    1.48
     rester
    1.48
     honn
    1.48
    
    1.43
    Activations Density 0.029%

    No Known Activations