© 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. 72781
    Prev
    Next
    INDEX
    Explanations

    Nigeria, Nigerian

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

    The neuron activates on mentions of “Nigeria” (and related demonyms).

    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
    t
    -3.05
    ндарт
    -3.02
    w
    -2.97
    u
    -2.73
    y
    -2.66
    h
    -2.63
     they
    -2.50
    es
    -2.44
    ();
    -2.42
    デュー
    -2.42
    POSITIVE LOGITS
    .
    2.88
    姈
    2.86
    骓
    2.48
    žena
    2.41
     cerdas
    2.25
    ARIOS
    2.23
     avesse
    2.20
    ва
    2.19
    驁
    2.19
    攫
    2.17
    Activations Density 0.003%

    No Known Activations