© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56540
    Prev
    Next
    INDEX
    Explanations

    image pixel data

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     URLs
    0.43
     homolog
    0.42
     照片
    0.40
     winner
    0.39
     categor
    0.39
     Fotos
    0.39
     ഇവ
    0.38
     Defendant
    0.38
    "]')
    0.38
    jar
    0.38
    POSITIVE LOGITS
     pixels
    0.66
    pixels
    0.64
    Pixels
    0.61
     grayscale
    0.58
     gray
    0.56
    像素
    0.56
     grayish
    0.56
     pixel
    0.54
     GRAY
    0.54
     bytes
    0.52
    Activations Density 0.181%

    No Known Activations