© 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. 12467
    Prev
    Next
    INDEX
    Explanations

    offensive internet slang

    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
     Hello
    0.51
    😊
    0.50
    Hello
    0.49
    হ্যালো
    0.49
     Hallo
    0.47
     Здравствуйте
    0.46
     würde
    0.45
     HelloWorld
    0.45
     Excuse
    0.45
     😍
    0.44
    POSITIVE LOGITS
     fucking
    0.62
     fuck
    0.51
     shit
    0.50
     merda
    0.48
     fucked
    0.48
    좆
    0.48
    fuck
    0.46
    shit
    0.45
     shitty
    0.45
     retarded
    0.42
    Activations Density 0.039%

    No Known Activations