© 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. 28940
    Prev
    Next
    INDEX
    Explanations

    sexual roleplay requests

    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
     appalled
    0.43
     treason
    0.42
    忡
    0.42
    提出
    0.41
     мозга
    0.39
    짊
    0.39
    seems
    0.39
     thải
    0.39
     बचना
    0.39
     मस्तिष्क
    0.38
    POSITIVE LOGITS
     complimentary
    0.57
     Canva
    0.55
     Value
    0.54
     Complimentary
    0.50
     V
    0.48
     we
    0.46
     We
    0.46
     معروف
    0.46
     Meer
    0.46
     Plus
    0.45
    Activations Density 0.004%

    No Known Activations