© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1566
    Prev
    Next
    INDEX
    Explanations

    eyelashes, eyeliner, mascara, eyebrows

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

    eye and lip cosmetics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     debtors
    0.57
     debtor
    0.56
    社會
    0.54
     للمعارف
    0.54
    शेखर
    0.52
    報告
    0.52
     psychiat
    0.52
    푐
    0.52
    अनुसूचित
    0.51
    शासन
    0.51
    POSITIVE LOGITS
     mascara
    0.88
     eyelashes
    0.87
     eyeliner
    0.77
     eyelash
    0.76
     lashes
    0.75
    睫
    0.74
     keratin
    0.72
     eyeshadow
    0.71
     nail
    0.70
     eyelid
    0.70
    Activations Density 0.102%

    No Known Activations