© 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. 32771
    Prev
    Next
    INDEX
    Explanations

    hydration and moisture

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

    terms related to skincare ingredients and moisturizing products.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    掃除
    -0.81
    Babylon
    -0.77
     disinfectant
    -0.77
     cleansing
    -0.76
    rmi
    -0.74
     cleanse
    -0.74
     camuf
    -0.72
     disinfect
    -0.71
     کف
    -0.71
     Clean
    -0.71
    POSITIVE LOGITS
     moisture
    1.52
     hydration
    1.45
     hume
    1.30
     thirsty
    1.27
    hydration
    1.26
     moisturizing
    1.13
    Hyd
    1.12
    锁
    1.12
     Hydration
    1.09
     hydrating
    1.09
    Activations Density 0.016%

    No Known Activations