© 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. 49263
    Prev
    Next
    INDEX
    Explanations

    job roles and employment

    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
    律师
    -0.88
    cycline
    -0.88
     Aktivitäten
    -0.80
    uchten
    -0.79
    📧
    -0.78
    orological
    -0.77
    wnia
    -0.76
    telse
    -0.75
     aeruginosa
    -0.75
     builder
    -0.75
    POSITIVE LOGITS
     employee
    2.23
     job
    2.08
     customer
    2.05
     employees
    1.98
     working
    1.98
     workplace
    1.92
     workers
    1.86
     customers
    1.84
     worker
    1.79
     work
    1.72
    Activations Density 0.043%

    No Known Activations