© 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. 10-GEMMASCOPE-RES-131K
    7. 12597
    Prev
    Next
    INDEX
    Explanations

    beauty pageant competitor

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

    This neuron strongly activates on tokens naming beauty pageants (e.g. “Miss World,” “Miss Universe,” and related national pageant titles and years).

    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
     is
    -1.65
    这些
    -1.43
    </h3>
    -1.43
    de
    -1.39
    .”
    -1.39
    躥
    -1.36
    Dec
    -1.35
     réinitial
    -1.35
    These
    -1.34
    these
    -1.33
    POSITIVE LOGITS
     शुर
    1.40
    lenght
    1.27
     before
    1.26
    Epidemiology
    1.25
     embarazada
    1.23
     todėl
    1.23
     rainha
    1.20
    🚎
    1.20
     atve
    1.20
    燹
    1.20
    Activations Density 0.014%

    No Known Activations