© 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. 59756
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     for
    -2.11
     your
    -1.56
     because
    -1.52
     ilustracji
    -1.43
     menghar
    -1.36
     by
    -1.34
     zám
    -1.34
     soğ
    -1.31
    すと
    -1.30
     yoğun
    -1.26
    POSITIVE LOGITS
    許多
    1.18
    aronder
    1.18
     Unterscheidung
    1.18
     Empfindung
    1.16
     גם
    1.14
            
    1.13
     Wirksamkeit
    1.11
     عبر
    1.08
    мом
    1.08
          
    1.08
    Activations Density 0.266%

    No Known Activations