© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7420
    Prev
    Next
    INDEX
    Explanations

    white Americans, women, supremacy

    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
     любого
    -1.62
    VIATIONS
    -1.48
    タブ
    -1.41
    其实是
    -1.36
    ….”
    -1.35
    
    -1.35
     between
    -1.34
     jūs
    -1.34
    ”).
    -1.34
     любой
    -1.34
    POSITIVE LOGITS
    攫
    1.52
    煽
    1.45
    rowser
    1.45
    ENCES
    1.45
    zzlement
    1.45
     cringe
    1.44
    cursions
    1.42
    rophi
    1.34
     It
    1.33
    deutsch
    1.31
    Activations Density 0.013%

    No Known Activations