© 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. 98397
    Prev
    Next
    INDEX
    Explanations

    African American history and culture

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

    The neuron strongly activates on capitalized named-entity tokens (people’s names, organizations, place/ethnic group labels, book or holiday titles, 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_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
     evange
    -0.88
     engra
    -0.82
     Evange
    -0.82
     evangel
    -0.80
    irmer
    -0.75
     averted
    -0.75
    mutlich
    -0.75
     Approval
    -0.74
     contagious
    -0.74
    FMT
    -0.74
    POSITIVE LOGITS
     Sank
    1.00
     africana
    0.99
     African
    0.96
     Africans
    0.92
     Hote
    0.91
     Maulana
    0.89
     self
    0.87
    ędzynarod
    0.87
    ICIONES
    0.82
     Afric
    0.81
    Activations Density 0.034%

    No Known Activations