© 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. 19830
    Prev
    Next
    INDEX
    Explanations

    insults and derogatory terms

    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
    оргаш
    -2.63
     céramique
    -2.58
     nových
    -2.55
    
    -2.52
    蕻
    -2.52
    宬
    -2.50
    婠
    -2.48
    ᾥ
    -2.48
    嘡
    -2.48
     tanques
    -2.47
    POSITIVE LOGITS
    ↵
    4.06
    ”,
    3.67
     Roughly
    2.83
    ’
    2.77
     Assuming
    2.70
     Importantly
    2.67
     Equally
    2.64
     Using
    2.59
     
    2.56
     Ideally
    2.53
    Activations Density 0.002%

    No Known Activations