© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67582
    Prev
    Next
    INDEX
    Explanations

    Worlds and their environments

    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
     who
    -2.27
     you
    -1.98
    ֶּ
    -1.85
     оружи
    -1.72
     чемпи
    -1.66
     аппети
    -1.59
    ıyors
    -1.55
     how
    -1.50
     know
    -1.48
     hyö
    -1.48
    POSITIVE LOGITS
    ׇ
    1.81
    ﻷ
    1.73
     mesmas
    1.70
     lojas
    1.63
    ﻹ
    1.52
    
    1.51
    诧异
    1.45
     Memiliki
    1.45
    ﷲ
    1.44
     Meningkatkan
    1.39
    Activations Density 0.394%

    No Known Activations