© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1492
    Prev
    Next
    INDEX
    Explanations

    currency codes (EUR, USD)

    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
     ($
    -0.98
     money
    -0.92
     often
    -0.85
     financial
    -0.85
     at
    -0.85
     there
    -0.85
     coins
    -0.84
    價
    -0.84
     costs
    -0.84
     (£
    -0.83
    POSITIVE LOGITS
     EUR
    1.18
    EUR
    1.05
     Swiss
    0.98
     USD
    0.94
     swiss
    0.91
     eur
    0.90
     épu
    0.89
    Swiss
    0.88
     Euro
    0.87
    kategori
    0.84
    Activations Density 0.019%

    No Known Activations