© 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. 94257
    Prev
    Next
    INDEX
    Explanations

    Pope names and papal terms

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     przeznac
    -0.82
     Regione
    -0.75
     comunale
    -0.74
     najczęściej
    -0.73
     polynomial
    -0.73
    ابط
    -0.73
     आया
    -0.72
    那时
    -0.72
     Madeira
    -0.71
     kaupung
    -0.70
    POSITIVE LOGITS
     Pope
    2.56
    Pope
    2.36
     pope
    2.28
     Vatican
    2.03
     cardinals
    1.65
     pap
    1.59
    Vat
    1.56
     papal
    1.55
    Pap
    1.53
     Cardinals
    1.53
    Activations Density 0.032%

    No Known Activations