© 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. 78204
    Prev
    Next
    INDEX
    Explanations

    monopoly, oligopoly, monoculture

    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
    Finanz
    -0.77
    ޖ
    -0.70
    bris
    -0.67
     Wentworth
    -0.66
    τοι
    -0.66
     denaro
    -0.65
     nonatomic
    -0.64
     Biggs
    -0.64
     endwhile
    -0.63
     diting
    -0.63
    POSITIVE LOGITS
     monopoly
    5.22
     моно
    4.56
     mono
    4.47
    mono
    4.44
    Mono
    4.34
     Mono
    4.25
     monopolies
    3.95
     monop
    3.91
     monopo
    3.88
     Monopoly
    3.66
    Activations Density 0.077%

    No Known Activations