© 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. 58859
    Prev
    Next
    INDEX
    Explanations

    lists of geographical data and names

    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
     reloading
    -0.74
     място
    -0.73
     Lithuania
    -0.73
     cutie
    -0.73
     lingerie
    -0.71
    ínguez
    -0.69
    Gamer
    -0.68
    mployed
    -0.68
    šli
    -0.68
    lugar
    -0.68
    POSITIVE LOGITS
     population
    1.59
    population
    1.13
     Population
    1.12
     coordinates
    1.08
     Capital
    1.05
    capital
    1.02
     elevation
    1.00
    Population
    1.00
     latitude
    0.99
     capital
    0.99
    Activations Density 0.012%

    No Known Activations