© 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. 35767
    Prev
    Next
    INDEX
    Explanations

    social injustices and privilege

    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
     will
    -1.28
     after
    -1.25
     hours
    -1.23
    عا
    -1.15
     weeks
    -1.15
    ulario
    -1.14
     behövs
    -1.13
     to
    -1.11
     gewiß
    -1.09
     pareció
    -1.09
    POSITIVE LOGITS
     السياس
    1.22
     パソコン
    1.21
     système
    1.17
    zech
    1.14
    vcut
    1.13
     Крым
    1.12
     ПОД
    1.10
    effects
    1.09
    appliquent
    1.09
     hiện
    1.05
    Activations Density 0.028%

    No Known Activations