© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49741
    Prev
    Next
    INDEX
    Explanations

    Chinese history and culture

    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
    ֶּ
    -1.20
     森林
    -1.04
     />
    -1.04
    投手
    -1.03
    pthread
    -0.99
    ּוֹ
    -0.99
     druid
    -0.98
     televiz
    -0.96
    Mô
    -0.96
    盦
    -0.94
    POSITIVE LOGITS
    Matteo
    1.06
     Heaven
    1.02
     Officials
    1.01
    道
    0.99
     officials
    0.94
     from
    0.94
     Buddhist
    0.93
     bamboo
    0.90
     Confucian
    0.90
     Han
    0.90
    Activations Density 0.073%

    No Known Activations