© 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. 3117
    Prev
    Next
    INDEX
    Explanations

    peptide, bradykinin, sequencing

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

    biochemical terminology related to enzymes, peptides, and protein structures.

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

    The neuron detects biochemical enzyme names—especially proteolytic enzymes (peptidases/proteases) ending in “-ase.”

    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
    pixel
    -0.79
    வத
    -0.75
    laze
    -0.71
     буенча
    -0.68
     shelves
    -0.67
     pixel
    -0.67
     Patriarch
    -0.67
    ぜ
    -0.66
     Boulevard
    -0.66
    WebApplication
    -0.66
    POSITIVE LOGITS
     peptide
    2.30
     peptides
    2.20
     Peptide
    1.95
    peptide
    1.91
    Peptide
    1.77
     Pep
    1.64
    pep
    1.63
     pep
    1.63
    Pep
    1.52
    肽
    1.37
    Activations Density 0.214%

    No Known Activations