© 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. 30745
    Prev
    Next
    INDEX
    Explanations

    colonial empire and territories

    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
    抬
    -0.81
    itars
    -0.80
     gefällt
    -0.72
     ಮ
    -0.72
    центра
    -0.71
     bobina
    -0.70
    mystery
    -0.70
    𝟬
    -0.69
     центра
    -0.69
     Built
    -0.69
    POSITIVE LOGITS
     colonies
    2.61
     colony
    2.53
     Colonies
    1.84
    colony
    1.79
     territories
    1.69
     Colony
    1.64
    Colony
    1.56
     possessions
    1.53
     colonie
    1.46
     colonial
    1.43
    Activations Density 0.058%

    No Known Activations