© 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. 10-GEMMASCOPE-RES-131K
    4. 65555
    Prev
    Next
    INDEX
    Explanations

    county names

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

    The neuron detects mentions of U.S. county names (as in “Shelby County,” “Brazoria County,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    躥
    -1.59
    塒
    -1.50
    硌
    -1.47
     ruine
    -1.44
     raken
    -1.44
     banane
    -1.41
     kambing
    -1.41
     armen
    -1.41
    still
    -1.38
     pouvons
    -1.38
    POSITIVE LOGITS
     or
    1.90
     County
    1.49
     While
    1.43
     As
    1.42
     If
    1.41
     For
    1.40
     Some
    1.35
     and
    1.35
     by
    1.34
     at
    1.27
    Activations Density 0.069%

    No Known Activations