© 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. 37966
    Prev
    Next
    INDEX
    Explanations

    cloning vectors and plasmids

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

    references to molecular biology vectors, plasmids, and cloning systems used in genetic engineering.

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

    The neuron detects specific molecular‐biology cloning constructs—especially named plasmid or vector insertions and related recombinant‐DNA terms.

    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
     hurtful
    -0.76
     búsquedas
    -0.73
     {.
    -0.71
    Somos
    -0.68
    Về
    -0.68
    tapis
    -0.67
     别
    -0.67
    แผ
    -0.66
     arquivo
    -0.65
    URLEncoder
    -0.65
    POSITIVE LOGITS
     vector
    1.53
     vectors
    1.49
    vector
    1.41
    destination
    1.06
     cloning
    1.02
    vectors
    1.01
     backbone
    0.99
    Vectors
    0.96
     destination
    0.94
    Vector
    0.90
    Activations Density 0.095%

    No Known Activations