© 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. 84649
    Prev
    Next
    INDEX
    Explanations

    privatisation or virtualization

    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
     aquel
    -1.94
    StoryboardSegue
    -1.80
    tamaris
    -1.71
    一流
    -1.70
    ной
    -1.69
    
    -1.68
    
    -1.66
    Figs
    -1.65
    ！（
    -1.63
    ՞
    -1.62
    POSITIVE LOGITS
    ↵
    1.88
    ㌧
    1.84
    ၞ
    1.84
    থ্য
    1.81
    廪
    1.76
     женщи
    1.75
     privati
    1.70
    蹚
    1.69
     insiste
    1.69
    on
    1.66
    Activations Density 0.003%

    No Known Activations