© 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. 63926
    Prev
    Next
    INDEX
    Explanations

    show off; show everyone

    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
     السياسة
    -0.93
    ᅲ
    -0.93
    探讨
    -0.92
    ѓ
    -0.90
    wości
    -0.89
    この
    -0.88
    StatusLabel
    -0.88
    却是
    -0.86
    Dengan
    -0.86
     Grizzlies
    -0.86
    POSITIVE LOGITS
     how
    2.25
     off
    1.53
     that
    1.50
     what
    1.28
     why
    1.25
     case
    1.24
    How
    1.21
     respect
    1.20
    boat
    1.19
     everyone
    1.17
    Activations Density 0.018%

    No Known Activations