© 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. 78984
    Prev
    Next
    INDEX
    Explanations

    see or look for

    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
    Karriere
    -0.84
    mortem
    -0.81
     منطقة
    -0.77
     ري
    -0.75
    ͭ
    -0.72
    vectors
    -0.71
    jasama
    -0.69
    bertura
    -0.69
     encuentras
    -0.69
     понятия
    -0.69
    POSITIVE LOGITS
     viewing
    2.06
     showing
    1.77
     Viewing
    1.72
    Viewing
    1.61
    viewing
    1.54
    Showing
    1.50
     Showing
    1.35
    showing
    1.34
     view
    1.29
     SHOWING
    1.27
    Activations Density 0.009%

    No Known Activations