© 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. 109171
    Prev
    Next
    INDEX
    Explanations

    targeted drug delivery

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

    scientific terms and phrases related to drug delivery, nanoparticles, and pharmaceutical research.

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

    The neuron strongly activates on paper titles and section headings (the high-level, capitalized phrases at the start of scientific sections).

    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
    𐌰
    -0.82
    менту
    -0.81
    抽
    -0.76
     ziren
    -0.76
    ન
    -0.75
     پدر
    -0.73
    NOPQRST
    -0.72
    мон
    -0.71
     пси
    -0.71
    wareness
    -0.69
    POSITIVE LOGITS
     delivery
    1.41
     cargo
    1.41
     payload
    1.26
     drug
    1.24
    cargo
    1.20
     stealth
    1.14
     targeting
    1.13
     deliver
    1.11
     encaps
    1.09
     tumor
    1.08
    Activations Density 0.246%

    No Known Activations