© 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. 34-GEMMASCOPE-RES-131K
    7. 58963
    Prev
    Next
    INDEX
    Explanations

    peaceful protest or demonstration

    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_34/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
    Ρ
    -0.78
    sensitivity
    -0.72
    主页
    -0.71
    villain
    -0.71
    وی
    -0.70
     trận
    -0.70
     efficacité
    -0.70
    หรับ
    -0.70
    ソナ
    -0.69
     Solid
    -0.69
    POSITIVE LOGITS
     peaceful
    5.16
     peacefully
    4.28
    peaceful
    3.94
    Peaceful
    3.89
     Peaceful
    3.69
     peace
    3.33
     PEACE
    3.14
    peace
    2.92
     мир
    2.84
    和平
    2.72
    Activations Density 0.031%

    No Known Activations