© 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. 19453
    Prev
    Next
    INDEX
    Explanations

    international financial institutions

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

    World Bank and IMF

    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
    uchos
    0.50
    étiques
    0.49
    úrg
    0.47
    ulfanyl
    0.45
    ície
    0.45
    ów
    0.45
     exponentially
    0.45
    树
    0.44
    otiti
    0.44
    ucho
    0.44
    POSITIVE LOGITS
    貸款
    0.71
     lender
    0.68
     lenders
    0.68
     lending
    0.63
     prést
    0.60
     Lender
    0.59
    loans
    0.58
    贷款
    0.57
     loans
    0.56
     USAID
    0.55
    Activations Density 0.034%

    No Known Activations