© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47994
    Prev
    Next
    INDEX
    Explanations

    familial [disease name]

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

    The neuron detects references to familial or hereditary medical conditions and diseases.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Iw
    -0.81
    kok
    -0.69
    useppe
    -0.68
    ubus
    -0.68
     Mobile
    -0.67
    Mauro
    -0.66
    magenta
    -0.66
    Iw
    -0.66
    著作
    -0.65
    ">(</
    -0.65
    POSITIVE LOGITS
    ount
    0.69
     صحیح
    0.67
     Timur
    0.66
    TC
    0.64
     alun
    0.64
    历
    0.63
     ESCAPE
    0.63
    賸
    0.63
    PARTITION
    0.63
    energy
    0.62
    Activations Density 0.060%

    No Known Activations