© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33498
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
     derivatives
    0.41
     delights
    0.41
    ⴻ
    0.41
    }`))
    0.41
    下了
    0.40
     desemb
    0.40
    ัญหา
    0.39
     produktów
    0.38
     yüzden
    0.37
    olesale
    0.36
    POSITIVE LOGITS
     message
    0.47
    鐫
    0.46
    message
    0.46
     natoque
    0.42
    语句
    0.42
    声明
    0.40
     pariatur
    0.40
    ম্পতি
    0.40
    pageNum
    0.39
     paragraph
    0.38
    Activations Density 0.001%

    No Known Activations