© 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. 37865
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities and officials

    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
    nador
    -1.01
    September
    -1.00
    皆さん
    -0.99
    taler
    -0.98
    October
    -0.96
    现在的
    -0.90
    December
    -0.90
    November
    -0.87
     במק
    -0.87
    ListItemIcon
    -0.87
    POSITIVE LOGITS
     US
    1.38
     senior
    1.34
     Britain
    1.29
     Australian
    1.16
     EU
    1.14
     Secretary
    1.12
     USA
    1.09
     Germany
    1.09
     German
    1.09
     Senior
    1.06
    Activations Density 0.044%

    No Known Activations