© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6922
    Prev
    Next
    INDEX
    Explanations

    Country followed by club, event, or music

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

    The neuron specifically detects occurrences of the capitalized word “Country.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    朏
    -2.77
    簠
    -2.50
    馓
    -2.23
    籥
    -2.11
    のよう
    -2.11
    ncia
    -2.08
     あります
    -2.08
    Ꝑ
    -2.06
    líben
    -2.05
    "")
    -2.02
    POSITIVE LOGITS
    an
    2.95
    The
    2.83
    婓
    2.67
    、
    2.63
    at
    2.61
    ֟
    2.56
     verheiratet
    2.55
    洐
    2.48
    ro
    2.47
    9
    2.34
    Activations Density 0.008%

    No Known Activations