© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33044
    Prev
    Next
    INDEX
    Explanations

    😈 roleplay, explicitly taboo content

    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
    О
    0.55
     О
    0.50
     adverts
    0.47
    categories
    0.47
    오늘
    0.47
     முக்கிய
    0.46
    となって
    0.46
    ０
    0.45
     اصلی
    0.45
    入口
    0.45
    POSITIVE LOGITS
    erequisite
    0.41
     milieu
    0.40
     behov
    0.40
     privé
    0.39
     swath
    0.39
     stash
    0.38
     irgend
    0.37
     setTasks
    0.37
     homeschool
    0.37
    äär
    0.36
    Activations Density 0.005%

    No Known Activations