© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 65452
    Prev
    Next
    INDEX
    Explanations

    formula, Russia, New, Web, Vitamin, Political

    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_all/layer_41_width_262k_l0_big
    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
     عائد
    0.40
    
    0.40
     bý
    0.39
    aggy
    0.38
     próximos
    0.38
    rosophila
    0.37
    수의
    0.37
    }"
    0.37
     -\
    0.37
     Balk
    0.37
    POSITIVE LOGITS
     веб
    0.41
    在线
    0.41
     ისინი
    0.40
     тре
    0.38
    豉
    0.35
    一个新的
    0.35
    它
    0.35
    查看
    0.34
    魈
    0.34
     దర్శ
    0.34
    Activations Density 0.000%

    No Known Activations