© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40479
    Prev
    Next
    INDEX
    Explanations

    class definitions following keywords

    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
     kompati
    -1.70
    ܖ
    -1.63
     Euró
    -1.56
     débuts
    -1.55
     suceder
    -1.55
     custos
    -1.54
    
    -1.54
     herunterladen
    -1.54
     aforementioned
    -1.53
     messen
    -1.53
    POSITIVE LOGITS
     with
    1.90
     for
    1.77
     они
    1.71
     of
    1.66
     they
    1.55
     only
    1.50
     mereka
    1.44
     as
    1.44
     их
    1.42
     not
    1.41
    Activations Density 0.095%

    No Known Activations