© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93789
    Prev
    Next
    INDEX
    Explanations

    office conversations and activities

    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
    Orts
    -0.91
    sockfd
    -0.90
     Airbnb
    -0.90
     homeowners
    -0.89
    ritage
    -0.87
     grandparents
    -0.87
     household
    -0.86
    Дом
    -0.85
     Homework
    -0.85
     households
    -0.84
    POSITIVE LOGITS
     office
    3.25
    office
    2.48
     colleagues
    2.45
     coworkers
    2.42
     workplace
    2.33
     offices
    2.28
     employees
    2.28
     employee
    2.25
     coworker
    2.22
     Office
    2.20
    Activations Density 0.110%

    No Known Activations