© 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. 40-GEMMASCOPE-2-RES-16K
    7. 7703
    Prev
    Next
    INDEX
    Explanations

    wearing, dressed, and posing

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sque
    0.46
     глю
    0.45
     testosterone
    0.45
    顫
    0.42
    颤
    0.41
     zwięks
    0.40
     trembled
    0.40
     breathed
    0.40
     відчу
    0.40
    穩
    0.40
    POSITIVE LOGITS
     wearing
    1.13
     Wearing
    1.05
    Wearing
    0.92
    wearing
    0.88
    穿着
    0.86
     dressed
    0.83
     smiling
    0.81
     poses
    0.73
     seated
    0.72
     shirtless
    0.70
    Activations Density 0.299%

    No Known Activations