© 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-65K
    7. 12506
    Prev
    Next
    INDEX
    Explanations

    testimony to, endure relentless, ancestry, class, common medical

    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_65k_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
     underpinning
    0.57
    regulatory
    0.56
     disruption
    0.54
    ندر
    0.52
     redraw
    0.52
     underpin
    0.52
     decarbon
    0.51
    埛
    0.51
     refocus
    0.51
     redesign
    0.50
    POSITIVE LOGITS
     WeChat
    0.82
     Xiao
    0.77
     Weibo
    0.76
     Chinese
    0.73
     netizens
    0.72
     Xia
    0.71
     Zhi
    0.70
     Qing
    0.69
     Qian
    0.69
     Dao
    0.67
    Activations Density 0.047%

    No Known Activations