© 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. 18072
    Prev
    Next
    INDEX
    Explanations

    Afghanistan, Kabul, Kunduz events

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

    Afghanistan and Persia

    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
     egip
    0.51
     Detroit
    0.48
     القاهرة
    0.48
     টিউ
    0.45
     اتھار
    0.45
     Tunisian
    0.45
     egyptian
    0.45
    癱
    0.45
     территориа
    0.44
    颀
    0.43
    POSITIVE LOGITS
    Afghanistan
    1.32
     Afghanistan
    1.29
     Afghan
    1.26
     Afghans
    1.26
    Afghan
    1.20
     Kabul
    1.12
     Afgan
    1.10
     Afgh
    1.07
     افغانستان
    0.99
     अफगानिस्तान
    0.98
    Activations Density 0.043%

    No Known Activations