© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98436
    Prev
    Next
    INDEX
    Explanations

    colonialism and imperialism

    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
    了起来
    -0.84
     integrated
    -0.82
     election
    -0.82
    買う
    -0.81
     community
    -0.81
     confirmed
    -0.79
     professional
    -0.76
    ▇
    -0.75
     adequado
    -0.73
    endalikan
    -0.73
    POSITIVE LOGITS
     colonial
    2.59
     colonialism
    2.52
     colon
    2.47
    colonial
    2.33
     colonization
    2.11
    colon
    2.06
     Colonial
    2.00
    Colonial
    2.00
     COLON
    1.98
    COLON
    1.95
    Activations Density 0.023%

    No Known Activations