© 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. 10-GEMMASCOPE-RES-131K
    7. 15459
    Prev
    Next
    INDEX
    Explanations

    templating this is

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    紲
    -1.90
    Ahol
    -1.86
    Kontra
    -1.77
     installieren
    -1.77
    länge
    -1.75
    plastik
    -1.75
    Krank
    -1.73
     fournisseur
    -1.70
     parfü
    -1.69
    鵯
    -1.67
    POSITIVE LOGITS
    .
    2.33
     "
    1.90
     to
    1.84
    :
    1.70
    \
    1.48
    '
    1.40
     Always
    1.39
    ...
    1.38
      
    1.38
    It
    1.36
    Activations Density 0.001%

    No Known Activations