© 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. 34-GEMMASCOPE-RES-131K
    7. 33791
    Prev
    Next
    INDEX
    Explanations

    cities and capitals

    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_34/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
    村民
    -1.23
     rural
    -1.12
     villagers
    -1.05
     villages
    -1.02
     Rural
    -1.01
    乡村
    -0.98
     countries
    -0.98
     Villages
    -0.94
    rural
    -0.94
     روست
    -0.93
    POSITIVE LOGITS
     city
    6.91
    city
    4.88
     cidade
    3.97
    City
    3.88
     City
    3.86
     città
    3.80
     ciudad
    3.80
    CITY
    3.70
     CITY
    3.42
     város
    3.33
    Activations Density 0.153%

    No Known Activations