© 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. 73640
    Prev
    Next
    INDEX
    Explanations

    in vitro transcription and translation

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

    scientific phrases related to laboratory techniques or experimental procedures, particularly "in vitro" studies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    न्दु
    -0.92
    requently
    -0.82
     geene
    -0.78
     keram
    -0.77
     هوشمند
    -0.77
    illoin
    -0.77
    segue
    -0.75
    retung
    -0.75
    diploma
    -0.75
     secretion
    -0.74
    POSITIVE LOGITS
     reaction
    1.23
     vitro
    1.23
     reactions
    1.14
     transcription
    1.13
     Reaction
    0.98
    Reaction
    0.97
    reaction
    0.96
     extract
    0.95
     REACTION
    0.88
     реак
    0.86
    Activations Density 0.114%

    No Known Activations