© 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. 49986
    Prev
    Next
    INDEX
    Explanations

    liquid-liquid extraction

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

    This neuron detects technical terms related to liquid-liquid interfaces, extractions, and phase partitioning in chemical/laboratory contexts.

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

    The neuron detects highly technical chemical‐engineering terms—especially those naming specialized extraction methods, membranes, and related polymer‐mediated processes.

    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
    質な
    -0.77
    bergen
    -0.74
    </thead>
    -0.74
     Chandra
    -0.70
    ложения
    -0.69
    Ờ
    -0.69
    SPATH
    -0.67
    網
    -0.67
     Traveler
    -0.65
     খ
    -0.65
    POSITIVE LOGITS
     extraction
    2.02
     Extraction
    1.96
    Extraction
    1.83
    extraction
    1.79
     extract
    1.66
     Extract
    1.59
    Extract
    1.58
    extract
    1.53
    萃
    1.49
     extracting
    1.48
    Activations Density 0.101%

    No Known Activations