© 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. 34-GEMMASCOPE-RES-131K
    4. 38265
    Prev
    Next
    INDEX
    Explanations

    preparation of loaded nanoparticles

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

    scientific terminology related to nanoparticles and pharmaceutical delivery systems.

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

    The neuron fires most strongly on parenthesized acronyms and highly technical formulation terms (e.g. “(NLCs)”), marking places where specialized abbreviations or jargon appear.

    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
     released
    -0.85
    使得
    -0.79
     dosage
    -0.77
     cantit
    -0.74
    Francois
    -0.73
    രാ
    -0.72
     figliu
    -0.72
    Roche
    -0.71
     lamina
    -0.71
     Stokes
    -0.71
    POSITIVE LOGITS
     stabilizer
    0.75
     Mulberry
    0.74
     feasibility
    0.74
    ಿ
    0.73
    致命
    0.73
     ressemble
    0.73
     versiones
    0.72
     purchaser
    0.70
    extField
    0.68
    Could
    0.68
    Activations Density 0.113%

    No Known Activations