© 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. 110502
    Prev
    Next
    INDEX
    Explanations

    Arabic names and 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
    '
    -1.95
    c
    -1.95
     anderes
    -1.78
    end
    -1.69
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.67
    get
    -1.66
     spezi
    -1.63
    ling
    -1.62
     zusätz
    -1.61
     sogen
    -1.58
    POSITIVE LOGITS
     you
    2.42
    ୈ
    1.97
     auch
    1.92
    
    1.90
    珦
    1.83
     teclas
    1.79
    亍
    1.74
    釭
    1.73
    𓐍
    1.73
     suman
    1.73
    Activations Density 0.006%

    No Known Activations