© 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. 97956
    Prev
    Next
    INDEX
    Explanations

    local government administration

    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
    本部
    -0.84
    esModule
    -0.82
    oldi
    -0.77
     campeón
    -0.77
    이션
    -0.77
    cería
    -0.76
    obio
    -0.76
    ineas
    -0.76
    šek
    -0.75
    不便
    -0.73
    POSITIVE LOGITS
     municipalities
    3.86
     municipal
    3.59
     local
    3.39
     municipality
    3.27
     cities
    3.23
     city
    2.84
    local
    2.83
    municipal
    2.64
     Local
    2.64
     county
    2.63
    Activations Density 0.095%

    No Known Activations