© 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. 52996
    Prev
    Next
    INDEX
    Explanations

    detailing sexual 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
    󰡕
    0.54
     അവ
    0.46
    ]',
    0.45
     בק
    0.45
     കൊണ്ട
    0.44
     박
    0.43
    🦵
    0.43
     !",
    0.43
    цію
    0.43
    iquent
    0.43
    POSITIVE LOGITS
     corporate
    0.52
     wellness
    0.50
     /
    0.48
     marketing
    0.46
     Wellness
    0.46
     criminal
    0.45
     dividend
    0.43
     market
    0.43
     consumer
    0.43
     automation
    0.43
    Activations Density 0.002%

    No Known Activations