© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103001
    Prev
    Next
    INDEX
    Explanations

    England and Wales

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

    This neuron detects mentions of “England” or “Wales” (including the phrase “England and Wales”).

    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
     one
    -1.91
     in
    -1.89
     any
    -1.84
     eight
    -1.78
     your
    -1.77
     two
    -1.73
     with
    -1.73
     four
    -1.67
     countless
    -1.65
     three
    -1.63
    POSITIVE LOGITS
    ’
    1.56
     accomod
    1.53
    ztes
    1.37
     misschien
    1.33
     Erklärung
    1.31
    sean
    1.30
     erläut
    1.30
     dising
    1.30
     本体
    1.30
     potrebbe
    1.30
    Activations Density 0.059%

    No Known Activations