© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45663
    Prev
    Next
    INDEX
    Explanations

    Chattanooga, Tennessee, Georgia

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

    This neuron responds to mentions of specific geographic place names (e.g., cities, counties, states).

    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
     ranchers
    -0.84
     picante
    -0.80
     Moreau
    -0.77
     Jede
    -0.76
     Sudanese
    -0.75
     زع
    -0.75
     metra
    -0.72
     Gorbachev
    -0.71
     Dons
    -0.69
    itter
    -0.68
    POSITIVE LOGITS
     Chattanooga
    2.02
     Cherokee
    1.11
     Tennessee
    1.04
     Georgia
    1.02
     Atlanta
    1.02
    ooga
    0.97
    Tennessee
    0.95
    Chat
    0.94
     Chat
    0.91
    Atlanta
    0.84
    Activations Density 0.029%

    No Known Activations