© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92683
    Prev
    Next
    INDEX
    Explanations

    skincare and beauty products

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

    beauty and skincare product descriptions and promotional content.

    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
    dig
    -0.75
     ajustable
    -0.75
    ंच
    -0.73
    DELETE
    -0.73
    Employment
    -0.71
    短
    -0.71
    ویری
    -0.71
     Employment
    -0.71
    обу
    -0.70
     tongues
    -0.70
    POSITIVE LOGITS
     care
    1.98
     skincare
    1.93
     products
    1.87
     beauty
    1.46
     cuidado
    1.40
     skin
    1.34
     treatments
    1.34
     Care
    1.32
    care
    1.30
     caring
    1.28
    Activations Density 0.030%

    No Known Activations