© 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. 70689
    Prev
    Next
    INDEX
    Explanations

    lists of countries and cities

    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
     which
    -1.80
      
    -1.53
     only
    -1.47
    mits
    -1.36
     has
    -1.34
    '
    -1.33
    it
    -1.32
       
    -1.30
     since
    -1.30
    as
    -1.29
    POSITIVE LOGITS
     veľmi
    1.80
     rápid
    1.49
     boyunca
    1.45
    Grupo
    1.42
    Saya
    1.41
    Iglesia
    1.39
     teď
    1.39
     tavsiye
    1.38
     práci
    1.38
    觧
    1.37
    Activations Density 0.121%

    No Known Activations