© 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. 15600
    Prev
    Next
    INDEX
    Explanations

    republic of country names

    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
     and
    -1.87
     maroc
    -1.70
     on
    -1.56
    刧
    -1.56
     milano
    -1.52
     suggested
    -1.48
    梘
    -1.48
    one
    -1.47
    ємо
    -1.45
     mercados
    -1.45
    POSITIVE LOGITS
     Debido
    1.65
     Puede
    1.62
    雳
    1.53
     they
    1.53
     Cualquier
    1.51
    Ensuite
    1.49
    朦
    1.48
    瘰
    1.46
     genügend
    1.46
    有很多
    1.46
    Activations Density 0.056%

    No Known Activations