© 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. 43552
    Prev
    Next
    INDEX
    Explanations

    diplomacy and foreign relations

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

    foreign relations and diplomacy

    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
     fárm
    0.56
     الكهرب
    0.54
    辊
    0.54
    锌
    0.53
     blanchâtre
    0.52
    𝕣
    0.51
     पशु
    0.50
     স্যাম
    0.50
    𓏧
    0.50
     elektry
    0.49
    POSITIVE LOGITS
    外交
    1.23
     Diplomacy
    1.23
     diplomacy
    1.19
     diplomatic
    1.16
     diplomats
    1.14
     Dipl
    1.09
     diplomat
    1.09
     дипло
    1.05
     diplom
    1.04
     Foreign
    1.03
    Activations Density 0.056%

    No Known Activations