© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105575
    Prev
    Next
    INDEX
    Explanations

    transgenic organisms

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

    The neuron activates for the word "transgenic" in scientific contexts, particularly when discussing genetically modified organisms.

    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
    </i>
    -2.77
     dasarnya
    -2.61
    觧
    -2.56
     поговори
    -2.55
    How
    -2.47
    ╿
    -2.38
     Когда
    -2.36
     conspicuously
    -2.34
    癀
    -2.34
    琹
    -2.33
    POSITIVE LOGITS
    踽
    2.81
    煦
    2.70
    方才
    2.69
     بنات
    2.59
    之为
    2.58
     elaboración
    2.55
     مناط
    2.50
     ,‬
    2.47
    圌
    2.44
    
    2.44
    Activations Density 0.004%

    No Known Activations