© 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. 108789
    Prev
    Next
    INDEX
    Explanations

    vanishing gradient

    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
    闂
    0.48
    u
    0.48
     stool
    0.48
     inspecting
    0.47
    اف
    0.46
     had
    0.45
     stools
    0.45
    使用者
    0.45
    使用
    0.44
    ب
    0.44
    POSITIVE LOGITS
    corollary
    0.48
     exhort
    0.47
     onları
    0.46
    кновен
    0.45
    yrı
    0.44
     Чтобы
    0.44
     Braves
    0.44
    ższ
    0.43
     onlar
    0.43
    št
    0.43
    Activations Density 0.001%

    No Known Activations