© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62960
    Prev
    Next
    INDEX
    Explanations

    gene constructs, plasmid vectors

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

    gene expression and genetic engineering terminology in scientific contexts.

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

    This neuron detects technical mentions of genetic engineering and gene therapy—specifically words around genes, vectors, and expression in a biomedical research context.

    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
     transform
    -0.90
     products
    -0.89
    Примечания
    -0.80
     involvement
    -0.79
     transformed
    -0.75
     analysis
    -0.74
    駅前
    -0.73
     coronel
    -0.72
     []:
    -0.69
     transformation
    -0.68
    POSITIVE LOGITS
     codon
    0.93
     exogenous
    0.93
     native
    0.81
    äus
    0.79
    ulage
    0.77
     naturlig
    0.76
    endront
    0.75
    łąd
    0.75
     papild
    0.74
    userService
    0.73
    Activations Density 0.161%

    No Known Activations