© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20821
    Prev
    Next
    INDEX
    Explanations

    plugin 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_65k_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
     беспо
    0.48
    Inn
    0.43
     backed
    0.42
     EXIST
    0.40
    enche
    0.40
    錶
    0.39
     D
    0.38
     società
    0.38
     nonchal
    0.38
     trust
    0.38
    POSITIVE LOGITS
    美丽
    0.43
    쁩
    0.43
    ஞ
    0.43
    美丽的
    0.43
     onderwerp
    0.42
     Почему
    0.41
     समृ
    0.41
     Nasıl
    0.41
     পাঁচটি
    0.41
     गेंदबाज
    0.40
    Activations Density 0.027%

    No Known Activations