© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106596
    Prev
    Next
    INDEX
    Explanations

    North Dakota government officials

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

    The neuron activates on U.S. city–state mentions in the “City, ST.” format (e.g. “Bismarck, N.D.”).

    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
    isamment
    -0.82
    ostro
    -0.79
     Ontario
    -0.74
    olc
    -0.73
     Erde
    -0.72
     Dicht
    -0.72
    oca
    -0.71
     Blüten
    -0.71
     analytically
    -0.71
    proken
    -0.69
    POSITIVE LOGITS
     Bismarck
    1.73
     ND
    1.62
     Fargo
    1.57
     UND
    1.52
    ND
    1.27
     Dakota
    1.27
    UND
    1.24
    Dakota
    1.16
     Sioux
    0.99
    nd
    0.98
    Activations Density 0.039%

    No Known Activations