© 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. 22-GEMMASCOPE-RES-131K
    7. 28552
    Prev
    Next
    INDEX
    Explanations

    regions and ethnicities

    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_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
    ּוֹ
    -1.67
    sements
    -1.34
    ַּ
    -1.20
    ֶּ
    -1.19
     derzeit
    -1.18
     bisher
    -1.18
     data
    -1.16
    וּ
    -1.16
     error
    -1.16
    iscus
    -1.16
    POSITIVE LOGITS
    ׇ
    1.57
     chrétienne
    1.54
     especially
    1.50
     chré
    1.45
     ویتامین
    1.40
    Especially
    1.39
     particularly
    1.34
    especially
    1.33
     religieuses
    1.30
     δὲ
    1.27
    Activations Density 0.112%

    No Known Activations