© 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. 103634
    Prev
    Next
    INDEX
    Explanations

    power and politics

    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
    •power-gemini

    No Comments

    Negative Logits
    Vá
    -0.78
    笑笑
    -0.74
    maturity
    -0.72
    lccccc
    -0.70
    三個
    -0.69
    気軽
    -0.68
    ppur
    -0.68
    の作品
    -0.67
     vá
    -0.67
     lö
    -0.67
    POSITIVE LOGITS
    幄
    0.86
    tabol
    0.84
    תה
    0.82
    ⣤
    0.79
     fiz
    0.79
     col
    0.78
    MONO
    0.77
    RIT
    0.75
     تز
    0.75
     Seer
    0.75
    Activations Density 0.045%

    No Known Activations