© 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. 10-GEMMASCOPE-RES-131K
    7. 105190
    Prev
    Next
    INDEX
    Explanations

    diseases and crises

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

    names of diseases and medical conditions.

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

    The neuron activates on mentions of major diseases or medical conditions (e.g. AIDS, HIV, diabetes, dementia, malaria).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    perience
    -1.55
    oprene
    -1.48
     publicó
    -1.48
    ร้าน
    -1.44
     guerres
    -1.37
    fficients
    -1.37
    过来了
    -1.37
    لقد
    -1.34
     oído
    -1.34
    imals
    -1.34
    POSITIVE LOGITS
    }
    1.39
    ȼ
    1.23
     moglie
    1.21
     Erase
    1.21
    related
    1.19
     and
    1.17
    も行
    1.17
    Beschreibung
    1.16
     bambino
    1.13
    やう
    1.13
    Activations Density 0.145%

    No Known Activations