© 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. 117072
    Prev
    Next
    INDEX
    Explanations

    financial income types

    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
    unitOfWork
    -0.88
    freep
    -0.77
    厥
    -0.75
     isValid
    -0.74
     tief
    -0.72
    fibonacci
    -0.71
    ఔ
    -0.69
    innoc
    -0.68
    ounen
    -0.68
    oun
    -0.67
    POSITIVE LOGITS
     income
    1.87
     earned
    1.33
     dividends
    1.30
    income
    1.30
    earned
    1.24
     incomes
    1.13
    Rental
    1.13
     dividend
    1.13
    Income
    1.09
    derived
    1.06
    Activations Density 0.016%

    No Known Activations