© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22734
    Prev
    Next
    INDEX
    Explanations

    hateful ideology

    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_40_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
    АТО
    0.46
     fy
    0.42
    약
    0.41
    实验
    0.40
     inject
    0.39
     menu
    0.39
    ából
    0.39
    注入
    0.38
    wise
    0.38
    ไว้
    0.38
    POSITIVE LOGITS
     对于
    0.42
    ۰
    0.39
     ដើម្បី
    0.39
     hiko
    0.38
     அவ்வ
    0.38
    陆续
    0.38
     ক্ষয়ক্ষতি
    0.36
    ekar
    0.36
     கூ
    0.35
     Наи
    0.35
    Activations Density 0.000%

    No Known Activations