© 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. 22-GEMMASCOPE-RES-131K
    7. 65671
    Prev
    Next
    INDEX
    Explanations

    Zimbabwe and related topics

    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_22/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
     Why
    -1.28
     a
    -1.27
     similar
    -1.26
     organize
    -1.25
     为什么
    -1.17
     examine
    -1.16
    示例
    -1.15
     How
    -1.13
    んだろう
    -1.13
    skjaer
    -1.13
    POSITIVE LOGITS
    Zimbabwe
    1.91
     Zimbabwe
    1.58
     Mugabe
    1.33
     nomenclature
    1.21
    Heidelberg
    1.20
     Kasus
    1.16
    eeeeeeee
    1.16
     táctil
    1.16
     Budaya
    1.16
     nimmer
    1.15
    Activations Density 0.011%

    No Known Activations