© 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. 58393
    Prev
    Next
    INDEX
    Explanations

    nursing home care

    np_acts-logits-general · gemini-2.5-flash-lite

    terms related to nursing homes, care facilities, and elder care services.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    vereignty
    -0.83
     ferti
    -0.81
     unemployed
    -0.80
     domestique
    -0.79
    orto
    -0.78
     Kund
    -0.77
     plages
    -0.77
    亵
    -0.77
    客气
    -0.77
    香りが
    -0.77
    POSITIVE LOGITS
     residents
    2.39
     nursing
    2.00
     caregivers
    1.95
     Residents
    1.88
    Residents
    1.81
     resident
    1.80
     caregiver
    1.74
     carers
    1.73
     care
    1.73
     Nursing
    1.73
    Activations Density 0.050%

    No Known Activations