© 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. 131032
    Prev
    Next
    INDEX
    Explanations

    republic of countries

    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
    檮
    -2.27
    
    -1.88
     crucial
    -1.86
     kleines
    -1.73
    '
    -1.72
    が多く
    -1.70
    扨
    -1.70
    と思って
    -1.70
    </em>
    -1.68
    凩
    -1.68
    POSITIVE LOGITS
    ſelves
    1.91
     invigor
    1.75
    Samedi
    1.66
     seems
    1.66
     famille
    1.66
    ø
    1.63
     și
    1.59
     людей
    1.57
     bernama
    1.55
    iniz
    1.54
    Activations Density 0.022%

    No Known Activations