© 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. 4288
    Prev
    Next
    INDEX
    Explanations

    telehealth and teleoperation

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

    terminology related to telemedicine and telehealth technologies.

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

    The neuron detects terms referring to online or “tele-” medical and health services (e.g. telehealth, telemedicine, virtual doctors, e-visits, online medical services).

    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
    umpe
    -0.84
    Ɠ
    -0.81
    passer
    -0.77
    ryk
    -0.75
    seurs
    -0.75
    */].
    -0.74
    listes
    -0.74
    κού
    -0.73
    Voter
    -0.73
    temperatur
    -0.73
    POSITIVE LOGITS
     tele
    3.17
     Tele
    2.98
    Tele
    2.64
     telehealth
    2.63
    tele
    2.39
     virtual
    2.08
     remote
    2.03
     теле
    1.98
    TELE
    1.90
     tel
    1.77
    Activations Density 0.032%

    No Known Activations