© 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. 53-GEMMASCOPE-2-RES-262K
    7. 50055
    Prev
    Next
    INDEX
    Explanations

    "are" followed by negative/vulgar language

    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_53_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
    瑗
    0.43
    畲
    0.41
    امل
    0.40
     Denison
    0.40
    鋐
    0.39
     uveden
    0.38
    多くの
    0.38
     Numerical
    0.38
    RELAND
    0.38
    镟
    0.38
    POSITIVE LOGITS
     fuck
    0.84
     badass
    0.84
     fucking
    0.83
     shitty
    0.80
     fucked
    0.79
     shit
    0.77
    fuck
    0.77
    Fuck
    0.77
    吐槽
    0.77
     bullshit
    0.75
    Activations Density 0.003%

    No Known Activations