© 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. 92231
    Prev
    Next
    INDEX
    Explanations

    market and economic activity

    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
    America
    -0.77
     автора
    -0.76
     Mayıs
    -0.75
     diure
    -0.75
    MARY
    -0.73
    ⇑
    -0.72
     récol
    -0.72
    protocols
    -0.71
    ##############
    -0.71
     jūs
    -0.71
    POSITIVE LOGITS
     #
    0.79
     autumn
    0.79
     instruments
    0.78
     inicios
    0.77
    澈
    0.76
     EEG
    0.75
    icum
    0.75
     cushioning
    0.74
     Instruments
    0.74
     brake
    0.74
    Activations Density 0.010%

    No Known Activations