© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 83727
    Prev
    Next
    INDEX
    Explanations

    words related to China

    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_40_width_262k_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
     वॉइस
    0.47
    ania
    0.42
     Lynn
    0.41
    aghan
    0.40
    ZA
    0.39
     ກ
    0.38
    za
    0.38
    Ƣ
    0.38
    یکه
    0.38
     Lu
    0.37
    POSITIVE LOGITS
     interfacing
    0.43
     siguientes
    0.42
     중국
    0.42
     asynchronously
    0.42
    মাম
    0.42
     চীন
    0.41
     interacting
    0.40
     الصين
    0.39
    intermedi
    0.39
     facilitating
    0.39
    Activations Density 0.001%

    No Known Activations