© 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. 22543
    Prev
    Next
    INDEX
    Explanations

    surnames of people

    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
     of
    -1.85
     for
    -1.70
     then
    -1.45
     mieszkańców
    -1.44
     they
    -1.38
     anledning
    -1.30
     at
    -1.27
     since
    -1.26
     either
    -1.22
     aktivitet
    -1.22
    POSITIVE LOGITS
    ﹍﹍
    1.59
    }}:
    1.56
     bañera
    1.41
    krę
    1.41
     who
    1.34
     maceta
    1.33
    を書
    1.30
     lakier
    1.28
     Fähigkeit
    1.27
    Гри
    1.26
    Activations Density 0.152%

    No Known Activations