© 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. 107650
    Prev
    Next
    INDEX
    Explanations

    Korean War

    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
    ComponentScan
    -0.76
    ätte
    -0.72
    ELE
    -0.71
    ワシ
    -0.71
    Christopher
    -0.70
    aved
    -0.69
    Std
    -0.66
     Cuc
    -0.66
    abytes
    -0.66
    пси
    -0.66
    POSITIVE LOGITS
     Korean
    4.34
    Korean
    3.58
     Korea
    3.41
    Korea
    2.78
     korean
    2.75
     Koreans
    2.33
    korean
    2.30
     korea
    2.25
    朝鮮
    2.02
    korea
    1.98
    Activations Density 0.047%

    No Known Activations