© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84321
    Prev
    Next
    INDEX
    Explanations

    African cultures and communities

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

    This neuron responds strongly to mentions of African demonyms, ethnic group or language names (e.g. “South African,” “Sotho,” “Zulu,” 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
     kutumia
    -1.43
     utaf
    -1.36
     kufanya
    -1.34
     nzuri
    -1.12
    began
    -1.11
     nying
    -1.10
     trà
    -1.09
    produ
    -1.03
     sauvages
    -1.03
    了一個
    -1.02
    POSITIVE LOGITS
    
    1.26
     muitas
    1.22
    ₦
    1.16
     many
    1.15
     are
    1.15
    vegli
    1.10
    ￡
    1.09
    ÇÕES
    1.09
    ⅖
    1.07
     preescolar
    1.05
    Activations Density 0.051%

    No Known Activations