© 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. 32825
    Prev
    Next
    INDEX
    Explanations

    county government and law enforcement entities

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

    The neuron fires on named county references (especially the word “County” in jurisdictional or law-enforcement contexts).

    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
     CITY
    -1.00
    цией
    -0.97
    getSelection
    -0.91
    embang
    -0.90
     {?}
    -0.87
    sions
    -0.86
    鱻
    -0.85
    皷
    -0.84
     lading
    -0.83
     好看
    -0.83
    POSITIVE LOGITS
     Sheriff
    1.80
     sheriff
    1.68
    Sheriff
    1.35
     Jail
    1.14
     courthouse
    1.09
     Chamber
    1.09
     Courthouse
    1.04
     Sher
    1.02
     jail
    1.00
     Extension
    1.00
    Activations Density 0.049%

    No Known Activations