© 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. 22-GEMMASCOPE-RES-131K
    7. 12848
    Prev
    Next
    INDEX
    Explanations

    genetic modification and biotechnology

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

    content related to genetic engineering, biotechnology, and CRISPR gene editing technology.

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

    The neuron detects terms referring to genetic modification or biotechnology—e.g. words like “GMO,” “genetic,” “modification,” “engineered,” “transgenic,” and related stems.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     warum
    -1.26
     all
    -1.23
     autobús
    -1.14
     baloncesto
    -1.14
     autobuses
    -1.12
    🌻
    -1.12
     hjälper
    -1.11
     boxeo
    -1.09
     aparcamiento
    -1.09
     thoſe
    -1.08
    POSITIVE LOGITS
    ższych
    1.48
     veränder
    1.30
    tilha
    1.28
     asisten
    1.27
    ษัท
    1.27
     diverso
    1.26
     bedeut
    1.23
    robat
    1.21
     research
    1.21
    Already
    1.16
    Activations Density 0.084%

    No Known Activations