© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40096
    Prev
    Next
    INDEX
    Explanations

    Ethiopia and Ethiopian

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

    This neuron activates on mentions of Ethiopia or related geographic/demonym forms (e.g., Ethiopian, Abyssinica).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    婼
    -1.46
    塒
    -1.45
    銛
    -1.42
    🍫
    -1.41
     our
    -1.34
    ثيق
    -1.32
    gée
    -1.30
     garansi
    -1.30
     fourrure
    -1.30
     czerwca
    -1.29
    POSITIVE LOGITS
     be
    1.32
     Ethiopian
    1.28
     în
    1.21
    ̙
    1.20
    gf
    1.20
     únicamente
    1.17
     chipped
    1.17
     clínicos
    1.16
    ،
    1.15
     Ethiopia
    1.14
    Activations Density 0.005%

    No Known Activations