© 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. 10775
    Prev
    Next
    INDEX
    Explanations

    diplomatic talks and leaders

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

    diplomatic visits and negotiations

    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
    玛
    0.74
    消费者
    0.68
    烧
    0.66
    电池
    0.66
     kullanım
    0.65
     ڈیٹا
    0.65
    减
    0.65
    蛏
    0.64
    应用
    0.63
    锅
    0.63
    POSITIVE LOGITS
     diplomatic
    1.48
     diplomats
    1.38
     diplomacy
    1.32
     diplom
    1.26
     diplomat
    1.22
     কূটনৈতিক
    1.22
    外交
    1.14
    dipl
    1.14
     дипло
    1.09
     negotiations
    1.07
    Activations Density 0.098%

    No Known Activations