© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4947
    Prev
    Next
    INDEX
    Explanations

    Chinese shareholding reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    颶
    0.71
    蓣
    0.71
    轵
    0.70
    鲔
    0.70
    睪
    0.69
    鲽
    0.67
    蓍
    0.66
    螟
    0.66
    蝰
    0.65
    椇
    0.65
    POSITIVE LOGITS
     Chinese
    1.82
     Beijing
    1.82
     China
    1.66
     Shanghai
    1.61
     चीन
    1.59
     중국
    1.58
    Beijing
    1.58
    Chinese
    1.55
     Nanjing
    1.53
     chinese
    1.52
    Activations Density 0.561%

    No Known Activations