© 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. 99437
    Prev
    Next
    INDEX
    Explanations

    economic and monetary terms

    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
    Meu
    -0.71
    亏
    -0.71
     dépend
    -0.71
    主的
    -0.69
     pregă
    -0.68
     microtub
    -0.68
     reaping
    -0.68
    imer
    -0.68
     obligatorio
    -0.67
    пат
    -0.67
    POSITIVE LOGITS
     money
    2.25
     Money
    1.81
    money
    1.70
    Money
    1.52
     MONEY
    1.38
     creation
    1.33
    MONEY
    1.27
     supply
    1.22
     création
    1.21
     Geld
    1.19
    Activations Density 0.013%

    No Known Activations