© 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. 66068
    Prev
    Next
    INDEX
    Explanations

    county

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

    The neuron detects the standard introductory phrasing of U.S. county descriptions (e.g. “X County is a county located in the U.S. state of Y; its …”).

    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
    states
    -0.88
     states
    -0.84
    IRST
    -0.81
    STATES
    -0.81
    setInt
    -0.79
     nazionale
    -0.79
     imprud
    -0.79
    States
    -0.79
    ęku
    -0.79
    ornos
    -0.78
    POSITIVE LOGITS
     county
    6.00
     County
    4.75
    county
    4.59
    County
    4.47
     COUNTY
    4.16
    COUNTY
    3.67
     counties
    3.13
    县
    3.05
    縣
    2.61
     Counties
    2.41
    Activations Density 0.069%

    No Known Activations