© 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. 98678
    Prev
    Next
    INDEX
    Explanations

    photo sensitizing agents

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

    technical or chemical terms in scientific writing, particularly related to imaging agents and chemical compounds.

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

    The neuron detects dense, technical scientific or clinical terminology—especially complex multi-syllable nouns and method/material names.

    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
     exportation
    -0.87
     !!}
    -0.77
    seled
    -0.77
    遺跡
    -0.76
    bello
    -0.74
    merate
    -0.74
    ricle
    -0.73
    ๘
    -0.73
     pharmacist
    -0.72
     речи
    -0.71
    POSITIVE LOGITS
     agents
    1.45
     agent
    1.41
     reagents
    1.39
     additives
    1.34
     chemicals
    1.30
     reagent
    1.27
     disinfectant
    1.24
     additive
    1.15
    agent
    1.09
     catalyst
    1.05
    Activations Density 0.418%

    No Known Activations