© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3147
    Prev
    Next
    INDEX
    Explanations

    Eurozone and European currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     végétal
    -0.75
     корпуса
    -0.71
     movable
    -0.71
     Tianjin
    -0.71
    Antecedentes
    -0.69
     caseros
    -0.69
    axiom
    -0.68
     forsø
    -0.67
    nour
    -0.66
    दार
    -0.66
    POSITIVE LOGITS
     euro
    1.55
     currency
    1.47
     Euro
    1.42
    zone
    1.28
     Currency
    1.26
    euro
    1.20
    currency
    1.17
     ECB
    1.13
    Currency
    1.11
     adopting
    1.11
    Activations Density 0.008%

    No Known Activations