© 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. 34-GEMMASCOPE-RES-131K
    7. 31657
    Prev
    Next
    INDEX
    Explanations

    compensation and benefits

    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
     remuneration
    -1.04
     disbursement
    -0.99
    financi
    -0.93
     Finances
    -0.91
     remuner
    -0.86
    ocate
    -0.86
     finances
    -0.84
    Ě
    -0.83
    reven
    -0.83
    Especificaciones
    -0.83
    POSITIVE LOGITS
     sick
    1.56
     health
    1.41
     pension
    1.30
     housing
    1.25
     healthcare
    1.23
     overtime
    1.21
     retirement
    1.17
     holiday
    1.17
     medical
    1.16
     travel
    1.14
    Activations Density 0.019%

    No Known Activations