© 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. 89735
    Prev
    Next
    INDEX
    Explanations

    municipalities and coalition governments

    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
     Namib
    -0.84
     nazionale
    -0.81
     فارسی
    -0.78
     Waikato
    -0.77
    rehension
    -0.77
     Pretoria
    -0.77
     perpé
    -0.76
    Nacional
    -0.76
    ativní
    -0.75
     Insta
    -0.75
    POSITIVE LOGITS
     council
    1.38
     municipality
    1.11
     Council
    1.06
     municipal
    1.05
    council
    1.04
     Gemeinder
    1.04
    Mayor
    1.02
     Mayor
    1.00
    Council
    0.99
     councillors
    0.95
    Activations Density 0.012%

    No Known Activations