© 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. 10-GEMMASCOPE-RES-131K
    4. 70752
    Prev
    Next
    INDEX
    Explanations

    white identity 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_10/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
    のこ
    -1.28
     también
    -1.24
     Categories
    -1.23
     relatos
    -1.23
     mereka
    -1.21
    !
    -1.21
     også
    -1.17
    onos
    -1.16
     où
    -1.16
     a
    -1.13
    POSITIVE LOGITS
     ferie
    1.20
    illez
    1.20
    Kunst
    1.18
    Доброго
    1.14
     mato
    1.12
     Wikiseite
    1.12
    Hilsen
    1.12
     afro
    1.11
     fellas
    1.11
     möglichen
    1.10
    Activations Density 0.059%

    No Known Activations