© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90510
    Prev
    Next
    INDEX
    Explanations

    codon usage and nucleic acid

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

    technical terminology related to genetics, RNA, and codons.

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

    The neuron is strongly triggered by references to genetic “codons” and related translation machinery (e.g. codon tables, tRNA, amino-acid translation).

    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
     día
    -0.77
    激素
    -0.76
     побе
    -0.76
    の日
    -0.75
     doc
    -0.69
     неболь
    -0.68
     promete
    -0.68
    mycompany
    -0.68
     dispu
    -0.68
    coffee
    -0.67
    POSITIVE LOGITS
     codon
    1.47
     wobble
    1.23
    codon
    1.20
    degener
    1.14
     degeneracy
    1.09
    degenerate
    1.04
    Cod
    1.03
     cod
    1.02
    cod
    0.96
     AUG
    0.95
    Activations Density 0.042%

    No Known Activations