© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    produce

    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
     podrás
    -1.55
    at
    -1.54
     you
    -1.53
    msford
    -1.44
     these
    -1.38
     být
    -1.35
     it
    -1.34
     tendrás
    -1.33
    才能
    -1.31
    óis
    -1.27
    POSITIVE LOGITS
     Produced
    1.80
    Producing
    1.48
     dihasilkan
    1.46
    канчи
    1.44
    sukienka
    1.43
     Produce
    1.42
    melissa
    1.42
    Qur
    1.40
     producen
    1.30
     seolah
    1.30
    Activations Density 0.102%

    No Known Activations