© 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. 118021
    Prev
    Next
    INDEX
    Explanations

    ethnic groups and peoples

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    beforeSend
    -0.72
    公开
    -0.69
    iLocal
    -0.69
     geï
    -0.69
    PARSE
    -0.68
    sendFile
    -0.67
     тури
    -0.67
    吃到
    -0.66
    rmızı
    -0.65
    litch
    -0.65
    POSITIVE LOGITS
     people
    3.81
     peoples
    3.27
    people
    2.67
    People
    2.64
     People
    2.55
     народа
    2.48
     Peoples
    2.44
     PEOPLE
    2.41
     peuple
    2.34
     peuples
    2.28
    Activations Density 0.080%

    No Known Activations