© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4404
    Prev
    Next
    INDEX
    Explanations

    skincare and skin health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     السياسي
    0.65
     финанси
    0.64
     політи
    0.63
     уголов
    0.59
     offshoring
    0.57
    运维
    0.57
     финансо
    0.56
    謀
    0.56
    政治
    0.56
     полномо
    0.56
    POSITIVE LOGITS
     skincare
    1.82
     moisturizer
    1.55
     skin
    1.49
     moistur
    1.45
     피부
    1.44
     Skin
    1.42
    Skin
    1.38
     moisturizing
    1.38
     Moistur
    1.38
     dermatologist
    1.35
    Activations Density 0.097%

    No Known Activations