© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81775
    Prev
    Next
    INDEX
    Explanations

    capital cities and places

    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
     SRI
    -0.87
     Karachi
    -0.77
     Antwerp
    -0.76
     Pom
    -0.74
     Grims
    -0.73
    Ṡ
    -0.71
     Vare
    -0.70
     Consulate
    -0.69
     Schulter
    -0.69
     Sharjah
    -0.68
    POSITIVE LOGITS
    Capital
    1.74
     Capital
    1.71
     capital
    1.65
     Canberra
    1.52
     Tallahassee
    1.47
     Capitol
    1.45
     capitol
    1.41
    capital
    1.40
    CAPITAL
    1.28
     CAPITAL
    1.27
    Activations Density 0.042%

    No Known Activations