© 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. 94182
    Prev
    Next
    INDEX
    Explanations

    patient satisfaction, safety, and advocacy

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

    references to patients in medical or healthcare contexts.

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

    The neuron activates whenever the text refers to “Patient” (i.e. mentions of patients). It effectively flags occurrences of the word “Patient.”

    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
     размеров
    -0.92
     proszę
    -0.87
    reeze
    -0.84
    such
    -0.82
     färg
    -0.81
    ricts
    -0.81
     reproductor
    -0.80
     spannend
    -0.80
    还有
    -0.80
     players
    -0.80
    POSITIVE LOGITS
     satisfaction
    1.07
     identification
    1.05
     centered
    1.02
     education
    1.02
     friendly
    1.00
     advocacy
    0.99
     centred
    0.97
     oriented
    0.94
     profile
    0.91
     advocate
    0.91
    Activations Density 0.085%

    No Known Activations