© 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. 38691
    Prev
    Next
    INDEX
    Explanations

    testing and tests

    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
     различные
    -1.25
     todėl
    -1.23
    了许多
    -1.22
     делает
    -1.18
     многие
    -1.17
    tierung
    -1.17
     并
    -1.14
                   
    -1.14
    irmanship
    -1.13
    もしくは
    -1.13
    POSITIVE LOGITS
     our
    1.37
    ".
    1.30
    ！"
    1.29
     "";
    1.27
     difp
    1.26
     terlaris
    1.25
     berkualitas
    1.24
    _"
    1.23
    jścia
    1.23
    ."'
    1.22
    Activations Density 0.088%

    No Known Activations