© 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. 64383
    Prev
    Next
    INDEX
    Explanations

    at the expense or cost

    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
    માં
    -0.86
    த்தில்
    -0.80
    Гаран
    -0.73
    lalom
    -0.71
     reverend
    -0.69
     дори
    -0.68
    ِّ
    -0.68
    Высота
    -0.67
     homeward
    -0.67
     būti
    -0.66
    POSITIVE LOGITS
     expense
    5.06
    expense
    3.78
     Expense
    3.30
     expenses
    3.23
    Expense
    3.19
     detriment
    2.70
    expenses
    2.55
     cost
    2.48
     kosz
    2.45
    Expenses
    2.34
    Activations Density 0.028%

    No Known Activations