© 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. 115572
    Prev
    Next
    INDEX
    Explanations

    emulsion

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

    The neuron strongly activates on technical terms and phrases related to emulsions—especially oil-in-water emulsions and their preparation 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
     کرب
    -0.76
     décès
    -0.73
    κέ
    -0.71
     antiseptic
    -0.69
    ndon
    -0.68
     blé
    -0.68
    Angeb
    -0.68
    LoadData
    -0.67
     readout
    -0.67
     restraint
    -0.66
    POSITIVE LOGITS
     emulsion
    2.55
     emulsions
    2.25
     em
    2.14
     emulsi
    2.11
    Em
    2.09
     Em
    2.00
    em
    1.63
     oil
    1.35
    乳
    1.19
    oil
    1.18
    Activations Density 0.084%

    No Known Activations