© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84847
    Prev
    Next
    INDEX
    Explanations

    historical periods and places

    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
     Pelop
    -0.91
     desired
    -0.89
     delegation
    -0.86
    annuation
    -0.85
     öfter
    -0.85
    冒険
    -0.84
     ± 
    -0.83
     службу
    -0.83
     requirements
    -0.82
     results
    -0.81
    POSITIVE LOGITS
     Britain
    1.41
     America
    1.29
     post
    1.27
     Italy
    1.27
     France
    1.18
     Germany
    1.16
     England
    1.14
     Spain
    1.05
     Poland
    1.03
     Ireland
    1.02
    Activations Density 0.073%

    No Known Activations