© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17763
    Prev
    Next
    INDEX
    Explanations

    skin tone and complexion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_l0_small_affine
    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
     दर्द
    0.40
    рья
    0.40
     जागरूक
    0.39
     मिलती
    0.38
    尕
    0.38
     चोट
    0.38
     ഡോ
    0.38
     ಘ
    0.38
    ખ્યા
    0.38
    卧室
    0.37
    POSITIVE LOGITS
     complexion
    0.65
    肤
    0.43
    顔
    0.41
    Booth
    0.41
     Tone
    0.41
     facial
    0.39
    膚
    0.39
     skin
    0.38
     얼굴
    0.38
    frame
    0.38
    Activations Density 0.042%

    No Known Activations