© 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-16K
    7. 3637
    Prev
    Next
    INDEX
    Explanations

    C++ code

    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_16k_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
     duc
    0.46
     लाल
    0.42
     রাতে
    0.40
    ý
    0.40
     .
    0.39
    ktr
    0.39
     maze
    0.38
    жды
    0.38
    古い
    0.38
    otor
    0.38
    POSITIVE LOGITS
     constexpr
    0.66
    constexpr
    0.61
    emplace
    0.59
    🤌
    0.56
     headwinds
    0.50
    nullptr
    0.48
     BOOST
    0.45
    鳇
    0.44
     pandemia
    0.43
     reimag
    0.43
    Activations Density 0.139%

    No Known Activations