© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27326
    Prev
    Next
    INDEX
    Explanations

    africa and african related words

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

    the word “Africa” or its adjectival form “African.”

    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
    縢
    -2.77
    1
    -2.70
    杁
    -2.47
    ar
    -2.39
    在自己
    -2.22
    '
    -2.19
     ส์
    -2.17
    部分が
    -2.17
     größe
    -2.13
    鹮
    -2.13
    POSITIVE LOGITS
    rierte
    2.36
    pidou
    2.33
     After
    2.33
     unrelenting
    2.25
    外人
    2.11
    ynı
    2.09
     multifaceted
    2.09
    
    2.02
    黎明
    2.02
    InlineData
    2.02
    Activations Density 0.024%

    No Known Activations