© 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. 34-GEMMASCOPE-RES-131K
    7. 77411
    Prev
    Next
    INDEX
    Explanations

    healthcare data and code

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

    technical or medical terminology in XML, APIs, and scientific papers.

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

    The neuron fires on tokens that look like code or markup identifiers—e.g. XML tags, class or field names, acronyms, and other technical/name tokens.

    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
    ViewHolder
    -0.81
     Sewing
    -0.77
    ütter
    -0.77
     Sub
    -0.75
     Stevens
    -0.73
    PubKey
    -0.72
    diendo
    -0.72
     Otto
    -0.71
     bacterial
    -0.71
    SerializedName
    -0.70
    POSITIVE LOGITS
    ଓ
    0.86
     Champlain
    0.84
    Patient
    0.83
    مثل
    0.83
    telecom
    0.81
     FH
    0.80
     patient
    0.78
    patient
    0.78
     colorés
    0.78
    europa
    0.77
    Activations Density 0.002%

    No Known Activations