© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8039
    Prev
    Next
    INDEX
    Explanations

    so that clauses of purpose

    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
     Préférences
    -1.30
    <bos>
    -1.30
    EQUALS
    -1.26
    ıkları
    -1.23
     では
    -1.22
     vidéos
    -1.22
     territoires
    -1.21
     variétés
    -1.20
     bré
    -1.18
     vétérina
    -1.18
    POSITIVE LOGITS
     cuando
    1.96
     to
    1.59
     avoid
    1.43
    useNewUrlParser
    1.41
     quando
    1.37
     чтобы
    1.35
    4
    1.34
     Our
    1.31
     ۳۰
    1.30
     infância
    1.27
    Activations Density 0.127%

    No Known Activations