© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9865
    Prev
    Next
    INDEX
    Explanations

    Northern Ireland and Ireland places

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

    Northern Ireland and Ulster

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

    Northern Ireland

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     Maharashtra
    0.42
     Surat
    0.40
    ேக
    0.39
     Shaikh
    0.39
     കമ്പ
    0.39
     ގ
    0.38
    asih
    0.37
    ёв
    0.37
    静岡
    0.37
    $;
    0.37
    POSITIVE LOGITS
     Belfast
    1.70
     Ulster
    1.44
     Donegal
    1.13
     Derry
    1.09
     Bally
    0.99
     Northern
    0.89
    Northern
    0.87
     Irish
    0.84
     irish
    0.82
     NI
    0.81
    Activations Density 0.095%

    No Known Activations