© 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. 45449
    Prev
    Next
    INDEX
    Explanations

    Shanghai or Chinese context

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

    SQL query parameters and identifiers

    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
    Chromosome
    0.62
     sıv
    0.61
    甾
    0.59
    鳃
    0.59
     вещества
    0.57
    辂
    0.56
    嘌
    0.56
    麃
    0.55
     microbiome
    0.55
     sıvı
    0.55
    POSITIVE LOGITS
    mybatis
    0.55
     service
    0.51
    ；
    0.51
     lottery
    0.49
    service
    0.49
     Shanghai
    0.47
     worried
    0.47
     上海
    0.46
    notify
    0.46
    weixin
    0.46
    Activations Density 0.000%

    No Known Activations