© 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. 83614
    Prev
    Next
    INDEX
    Explanations

    chromosome analysis and genetic anomalies

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

    scientific content related to chromosomes, karyotypes, and genetic abnormalities.

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

    The neuron strongly activates on numeric tokens (digits and multi‐digit numbers) in the text.

    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
    åga
    -0.77
    วม
    -0.74
    
    -0.73
     breakdown
    -0.70
    combobox
    -0.69
     sapere
    -0.68
    breakdown
    -0.67
     surnames
    -0.66
     getFile
    -0.66
     Suppression
    -0.66
    POSITIVE LOGITS
     kary
    1.23
     Kline
    1.09
    kary
    1.09
     XX
    1.03
     tris
    0.99
     Tris
    0.95
     mosaic
    0.94
    Kary
    0.93
    XX
    0.91
    tris
    0.90
    Activations Density 0.082%

    No Known Activations