© 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. 22-GEMMASCOPE-RES-131K
    7. 128187
    Prev
    Next
    INDEX
    Explanations

    expenses and costs

    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_22/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
    FFECT
    -1.12
    XmlSchema
    -1.06
     Seuss
    -1.05
    もうすぐ
    -1.03
    אבל
    -1.00
    ÑO
    -1.00
    ใหม่
    -0.99
    wortet
    -0.99
     бъ
    -0.99
    pakah
    -0.99
    POSITIVE LOGITS
     expenses
    1.50
     costs
    1.38
     travel
    1.33
     for
    1.33
     expenditure
    1.27
     ihtiyaç
    1.21
     usage
    1.18
     expense
    1.14
     cost
    1.13
     incurred
    1.13
    Activations Density 0.014%

    No Known Activations