© 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. 10-GEMMASCOPE-RES-131K
    7. 87220
    Prev
    Next
    INDEX
    Explanations

    reverse transcription and polymerase

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

    This neuron detects molecular biology terms related to reverse transcription and DNA/RNA processing, particularly focusing on RT (reverse transcriptase) and transcription processes.

    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_10/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
    as
    -1.92
     lakini
    -1.88
     și
    -1.84
    up
    -1.82
    其妙
    -1.75
     wako
    -1.70
    開啟
    -1.67
     häl
    -1.67
    試試
    -1.67
     uye
    -1.66
    POSITIVE LOGITS
    )
    2.20
     oficialmente
    1.90
    ibold
    1.84
     '
    1.77
     coordenadas
    1.75
     pregunt
    1.74
    ."
    1.72
     cualquier
    1.70
     acompañ
    1.67
    百合
    1.59
    Activations Density 0.076%

    No Known Activations