© 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. 119395
    Prev
    Next
    INDEX
    Explanations

    health care, risk management, aged care

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

    words and phrases related to healthcare facilities, services, and professional care settings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron consistently fires on occurrences of “care” (and closely related care-context terms) in healthcare or aged-care settings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Scholarship
    -0.80
     Faculty
    -0.75
     exams
    -0.75
    ])))
    -0.73
     exam
    -0.73
     Educational
    -0.73
     marriage
    -0.72
     ]
    -0.72
     memorable
    -0.71
    Ճ
    -0.70
    POSITIVE LOGITS
     milieu
    0.97
     foon
    0.83
     Medication
    0.81
     هول
    0.81
    膑
    0.79
    덥
    0.78
    Medication
    0.78
     Bastion
    0.77
     theorist
    0.75
    Hc
    0.75
    Activations Density 0.009%

    No Known Activations