© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2648
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    简单的
    0.36
     Esa
    0.34
     ONU
    0.34
    IndexPath
    0.34
    ানি
    0.34
    儿
    0.34
     Estas
    0.33
    पात
    0.33
    νον
    0.33
    妇
    0.33
    POSITIVE LOGITS
     frustration
    0.39
     chaos
    0.39
    chaos
    0.38
     ዋና
    0.38
     frust
    0.38
    処理
    0.38
     stumble
    0.37
    ítulo
    0.37
     abgeschlossen
    0.35
     co
    0.35
    Activations Density 0.519%

    No Known Activations