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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10157
    Prev
    Next
    INDEX
    Explanations

    running and marathons

    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
     عدم
    -1.25
     efek
    -1.22
     hotly
    -1.20
     toate
    -1.20
    wherein
    -1.19
     gdy
    -1.18
     ۱۵
    -1.17
     ζωή
    -1.16
    してしまった
    -1.16
     coloré
    -1.16
    POSITIVE LOGITS
     either
    1.38
     isn
    1.20
     during
    1.18
     become
    1.15
      
    1.12
     my
    1.09
     it
    1.08
    ervé
    1.07
     維
    1.05
     allows
    1.04
    Activations Density 0.048%

    No Known Activations