© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47289
    Prev
    Next
    INDEX
    Explanations

    intersectional social identities

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    형
    -0.85
    onymes
    -0.82
    декват
    -0.80
    handlungen
    -0.77
     dun
    -0.77
    ido
    -0.75
     الرياضيه
    -0.73
    양
    -0.72
     icono
    -0.72
    }`}
    -0.71
    POSITIVE LOGITS
     identities
    1.95
     identity
    1.91
     oppression
    1.68
     intersection
    1.59
    identity
    1.53
    身份
    1.48
     oppressed
    1.44
     Identity
    1.43
     intersecting
    1.37
     marginalized
    1.33
    Activations Density 0.022%

    No Known Activations