© 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-262K
    7. 36586
    Prev
    Next
    INDEX
    Explanations

    profanity and vulgarity

    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_262k_l0_medium
    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
     darling
    0.81
    🎀
    0.81
     lovely
    0.76
    💗
    0.75
    💖
    0.73
     beloved
    0.72
     adorable
    0.72
    ♡
    0.71
     Lovely
    0.71
     dreamy
    0.70
    POSITIVE LOGITS
     pissed
    0.90
     bullshit
    0.85
     shitty
    0.85
     crap
    0.83
    Fuck
    0.80
    俺
    0.80
     merda
    0.78
     shit
    0.77
     asshole
    0.77
     thằng
    0.77
    Activations Density 0.005%

    No Known Activations