© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69951
    Prev
    Next
    INDEX
    Explanations

    medical diagnostics and conditions

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

    scientific or medical terms, particularly in foreign language contexts or specialized vocabulary.

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

    The neuron fires on subword fragments characteristic of complex scientific or medical terminology.

    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
     they
    -1.90
    They
    -1.73
     Tetapi
    -1.70
     -
    -1.52
     Mereka
    -1.48
     their
    -1.46
    "
    -1.45
     that
    -1.44
    任何
    -1.43
     Ayrıca
    -1.39
    POSITIVE LOGITS
    phòng
    1.73
    ビリ
    1.59
    着她
    1.52
    着一个
    1.45
     preciosas
    1.45
     bocetos
    1.41
     sonriente
    1.40
     activiteiten
    1.40
     materiaal
    1.39
     espejos
    1.38
    Activations Density 0.184%

    No Known Activations