© 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. 111067
    Prev
    Next
    INDEX
    Explanations

    oils and fatty acids

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

    ingredients in skincare and beauty products.

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

    The neuron specializes in spotting rich, promotional cosmetic and skincare descriptors—especially nourishing, hydrating, and ingredient‐focused terms in product descriptions.

    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
     starch
    -0.79
     probiotic
    -0.78
    xml
    -0.76
    HCl
    -0.73
    floxacin
    -0.71
     probiotics
    -0.70
     المياه
    -0.70
    CLEAN
    -0.70
     fiber
    -0.68
    reda
    -0.68
    POSITIVE LOGITS
     oil
    1.25
     Oil
    1.12
     oils
    1.02
     castor
    0.98
     carrier
    0.98
    huile
    0.97
     canola
    0.93
     OIL
    0.91
     argan
    0.91
    Fatty
    0.91
    Activations Density 0.009%

    No Known Activations