© 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. 34-GEMMASCOPE-RES-131K
    7. 107890
    Prev
    Next
    INDEX
    Explanations

    peace and anti-war activism

    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
     geh
    -0.74
    Sản
    -0.73
    AspNetCore
    -0.72
    Vielen
    -0.71
    界
    -0.70
    𝛽
    -0.70
     Capcom
    -0.70
    kao
    -0.69
    щий
    -0.69
    ESPN
    -0.68
    POSITIVE LOGITS
     peace
    4.28
     Peace
    3.56
    peace
    3.50
    Peace
    3.48
     pacif
    2.97
     PEACE
    2.86
    PEACE
    2.42
     paix
    1.99
    和平
    1.98
    平和
    1.97
    Activations Density 0.073%

    No Known Activations