© 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. 82961
    Prev
    Next
    INDEX
    Explanations

    colonial transportation and settlers

    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
    ﻟ
    -0.84
     شیک
    -0.82
     Gey
    -0.77
    (")
    -0.77
    θρω
    -0.75
    綜合
    -0.73
     Tiro
    -0.73
    zeige
    -0.73
     Carmel
    -0.72
     комму
    -0.70
    POSITIVE LOGITS
     convict
    1.53
     convicts
    1.16
     colonial
    1.16
     settlers
    1.15
     frontier
    1.05
     settler
    1.03
     Colonial
    1.02
     colon
    0.97
    Sydney
    0.95
     transportation
    0.93
    Activations Density 0.035%

    No Known Activations