© 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. 92443
    Prev
    Next
    INDEX
    Explanations

    patient confidentiality

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

    content related to privacy, confidentiality, and information security.

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

    The neuron activates on mentions of confidentiality or privacy protection statements (e.g., references to laws, regulations, or guarantees that client or user information is kept confidential).

    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
    нето
    -0.82
    даго
    -0.78
     vulga
    -0.76
     Compliance
    -0.75
    hematical
    -0.75
    textrm
    -0.74
    colony
    -0.73
     Kommun
    -0.73
     deficit
    -0.73
     keben
    -0.72
    POSITIVE LOGITS
     confidentiality
    3.70
     confidential
    3.00
     Confidentiality
    2.75
     confid
    2.50
     privacy
    2.28
     Confidential
    2.14
    Confidential
    2.06
     secrecy
    1.91
     strictest
    1.91
    conf
    1.85
    Activations Density 0.044%

    No Known Activations