© 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. 35673
    Prev
    Next
    INDEX
    Explanations

    Belgium and Belgian references

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

    Belgium and Brussels

    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
     Riley
    0.53
     Oahu
    0.52
     Mojave
    0.48
     Kauai
    0.47
     Yosemite
    0.46
     Pronghorn
    0.46
    얽
    0.46
    🏜
    0.45
    anyon
    0.43
     California
    0.43
    POSITIVE LOGITS
     Belgium
    1.84
     Belgian
    1.77
    Belgium
    1.63
     Belgi
    1.45
     belg
    1.43
     België
    1.43
     Belgien
    1.40
     Flemish
    1.39
     Belgique
    1.38
     Brussels
    1.36
    Activations Density 0.056%

    No Known Activations