© 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. 45628
    Prev
    Next
    INDEX
    Explanations

    patient confidentiality

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

    content related to medical ethics and patient rights in healthcare settings.

    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
    をかけて
    -0.84
    こいつ
    -0.77
    لينا
    -0.75
     parka
    -0.74
    虑
    -0.73
    若干
    -0.73
    coordinator
    -0.71
    SUNDAY
    -0.71
     todavía
    -0.71
    celona
    -0.70
    POSITIVE LOGITS
     clients
    1.02
     fb
    0.93
     client
    0.92
    ８
    0.90
     dual
    0.90
     colleagues
    0.88
    Clients
    0.87
    ４
    0.84
     benefic
    0.84
     colegas
    0.84
    Activations Density 0.014%

    No Known Activations