© 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. 37052
    Prev
    Next
    INDEX
    Explanations

    ambassador to countries or in cities

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

    embassies and ambassadors

    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
    aket
    0.48
     여자
    0.46
    DIRS
    0.45
    RootDir
    0.45
     Sponge
    0.44
     Solid
    0.44
    vány
    0.43
    蔻
    0.42
     Yeti
    0.41
     कार्यकर्ता
    0.41
    POSITIVE LOGITS
     diplomatic
    0.83
     diplomats
    0.81
     embassies
    0.79
     embassy
    0.79
     diplom
    0.76
     diplomat
    0.76
     ambassador
    0.75
     diplomacy
    0.74
     ambassadors
    0.73
     Embassy
    0.73
    Activations Density 0.020%

    No Known Activations