© 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. 98334
    Prev
    Next
    INDEX
    Explanations

    inclusive economic growth

    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
    żą
    -0.88
    タンク
    -0.82
    ruma
    -0.81
     мальчик
    -0.81
     introduit
    -0.79
    铖
    -0.79
    gant
    -0.78
    ленные
    -0.77
     soprav
    -0.77
    Mga
    -0.75
    POSITIVE LOGITS
     growth
    1.90
     Growth
    1.55
    growth
    1.50
    Growth
    1.30
     GDP
    1.29
     jobs
    1.28
     Inclusive
    1.27
     crecimiento
    1.26
     GROWTH
    1.24
     inclusive
    1.22
    Activations Density 0.027%

    No Known Activations