© 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. 103303
    Prev
    Next
    INDEX
    Explanations

    council and district government

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of geographic or administrative place names (e.g. parishes, districts, councils, counties, municipalities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    mę
    -0.82
     creativo
    -0.81
     BATTERY
    -0.76
    county
    -0.76
     barra
    -0.74
    parks
    -0.74
    Commissioner
    -0.71
    Supervisor
    -0.71
    Curi
    -0.70
    guint
    -0.70
    POSITIVE LOGITS
     council
    1.66
     Council
    1.45
     councils
    1.23
    Council
    1.20
    council
    1.09
     COUNCIL
    1.03
     kommunen
    0.95
     municipality
    0.91
    UNCIL
    0.88
     Councils
    0.86
    Activations Density 0.048%

    No Known Activations