© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32349
    Prev
    Next
    INDEX
    Explanations

    nourish and moisturize hair

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

    The neuron activates on words describing moisturizing, hydrating, or nourishing benefits 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
     climá
    -0.94
    ּוֹ
    -0.90
    timis
    -0.89
    otomy
    -0.85
    onces
    -0.85
    empty
    -0.83
    xdb
    -0.83
    ectomy
    -0.82
    vings
    -0.82
    jeta
    -0.82
    POSITIVE LOGITS
     moisturi
    1.91
     nourishment
    1.80
     nourish
    1.63
     nour
    1.57
    moist
    1.55
     nourishing
    1.55
     hydration
    1.54
    滋
    1.49
    Nour
    1.42
     moisturizing
    1.40
    Activations Density 0.028%

    No Known Activations