© 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. 10-GEMMASCOPE-RES-131K
    7. 66025
    Prev
    Next
    INDEX
    Explanations

    privilege and oppression

    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
     for
    -2.13
     from
    -1.77
     this
    -1.73
     at
    -1.63
     because
    -1.57
     their
    -1.53
     between
    -1.52
     on
    -1.48
     should
    -1.38
    there
    -1.30
    POSITIVE LOGITS
     préféré
    1.46
     donde
    1.44
     falda
    1.43
     sudadera
    1.37
     testé
    1.34
     необходи
    1.32
     dekol
    1.32
     sokak
    1.30
     autonomie
    1.30
     ouverture
    1.30
    Activations Density 0.026%

    No Known Activations