© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22883
    Prev
    Next
    INDEX
    Explanations

    personalization and customization

    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
    Negative Logits
    "
    -1.91
     MUCH
    -1.75
     Then
    -1.75
     At
    -1.72
    .
    -1.70
     Of
    -1.68
     So
    -1.65
     On
    -1.63
     Let
    -1.62
     Not
    -1.61
    POSITIVE LOGITS
    媜
    2.17
     camisetas
    1.88
     comentários
    1.80
     สวย
    1.75
     сына
    1.74
    螣
    1.66
    にします
    1.65
    Sonntag
    1.64
     bidra
    1.64
     свадь
    1.63
    Activations Density 0.038%

    No Known Activations