© 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. 10-GEMMASCOPE-RES-131K
    7. 38763
    Prev
    Next
    INDEX
    Explanations

    empires and political entities

    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_10/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
    '
    -4.56
    2
    -3.67
    菒
    -3.25
    1
    -3.16
    \
    -2.81
    鉏
    -2.78
     erhi
    -2.78
    7
    -2.70
    槼
    -2.69
    的很
    -2.63
    POSITIVE LOGITS
     While
    3.05
     During
    2.98
     If
    2.80
     playful
    2.77
     Before
    2.75
     viviendo
    2.70
     When
    2.69
     After
    2.63
     tocó
    2.61
     seductive
    2.59
    Activations Density 0.003%

    No Known Activations