© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1624
    Prev
    Next
    INDEX
    Explanations

    Soviet Union history and Gulag camps

    np_acts-logits-general · gemini-2.5-flash-lite

    Soviet Union and its era

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    股东
    0.71
    荭
    0.61
    账
    0.61
    合约
    0.60
    鲔
    0.60
    售价
    0.58
    馔
    0.58
    leValue
    0.57
    镁
    0.57
    睑
    0.57
    POSITIVE LOGITS
     Soviet
    1.75
     Stalin
    1.66
     USSR
    1.60
     soviet
    1.55
     Leningrad
    1.44
     Soviets
    1.43
     Moscow
    1.42
    Soviet
    1.41
     communist
    1.40
     소련
    1.40
    Activations Density 0.087%

    No Known Activations