© 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. 31-GEMMASCOPE-2-RES-262K
    7. 205328
    Prev
    Next
    INDEX
    Explanations

    explaining offensive words

    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_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
    ሮችን
    0.49
    参加
    0.46
    典型的
    0.46
    ordinated
    0.45
    Ки
    0.45
    棹
    0.45
    adle
    0.44
    ag
    0.44
    痤
    0.43
     ನಂತರ
    0.43
    POSITIVE LOGITS
     involuntarily
    0.56
     unsettling
    0.53
     eternally
    0.50
     peacefully
    0.50
     distrust
    0.49
     erect
    0.48
     otherworldly
    0.48
     ambush
    0.48
     mischievous
    0.48
     unsett
    0.48
    Activations Density 0.002%

    No Known Activations