© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32689
    Prev
    Next
    INDEX
    Explanations

    genetic traits and improvements

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

    This neuron detects scientific and agricultural terminology related to plant genetics, breeding, and crop traits.

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

    The main thing this neuron does is detect numeric sequences and identifiers (digits, years, codes, and hyphenated numbers).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    columnwidth
    -1.23
     guantes
    -1.23
    breos
    -1.23
    Даже
    -1.22
     tornillos
    -1.17
    issez
    -1.16
    𝒉
    -1.16
    cessite
    -1.16
     voulait
    -1.13
    éricos
    -1.13
    POSITIVE LOGITS
     to
    1.57
     that
    1.41
     improvement
    1.38
     in
    1.30
     traits
    1.24
     on
    1.23
     trait
    1.22
    奬
    1.22
     improvements
    1.21
     expressed
    1.15
    Activations Density 0.149%

    No Known Activations