© 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. 34-GEMMASCOPE-RES-131K
    4. 60220
    Prev
    Next
    INDEX
    Explanations

    diversity and inclusion

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Jerusalén
    -0.90
    hasilkan
    -0.89
     Archivado
    -0.81
    Ǹ
    -0.79
    LAM
    -0.77
     végét
    -0.77
     probado
    -0.77
     khuyên
    -0.77
     udah
    -0.76
    λια
    -0.76
    POSITIVE LOGITS
     diversity
    4.88
     Diversity
    4.38
    Diversity
    4.00
    diversity
    3.81
     diversidad
    2.77
     DEI
    2.70
     inclusion
    2.61
     inclu
    2.58
    IVERSITY
    2.53
     Inclusion
    2.44
    Activations Density 0.036%

    No Known Activations