© 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. 102189
    Prev
    Next
    INDEX
    Explanations

    Afro- or Castro- related names/places

    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
    昻
    -2.80
    🡺
    -2.70
    〠
    -2.67
     Of
    -2.52
    ).
    -2.50
    
    -2.50
    䜣
    -2.45
    ☫
    -2.39
    ୩
    -2.36
     ostavi
    -2.34
    POSITIVE LOGITS
     Could
    2.59
    ’
    2.22
     ウィメンズ
    2.11
    鉭
    2.06
     Incredible
    1.98
     Might
    1.93
     Couple
    1.90
     authorizing
    1.89
     คุณ
    1.88
    —
    1.83
    Activations Density 0.001%

    No Known Activations