Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5215
    Prev
    Next
    INDEX
    Explanations

    specific names or qualifiers

    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
    ชน์
    0.28
    ᠴ
    0.26
     اربعه
    0.26
    들과
    0.25
    งาน
    0.25
    Kons
    0.24
    軍
    0.24
    経営
    0.24
    funk
    0.24
    ᠶ
    0.24
    POSITIVE LOGITS
     appunto
    0.29
     either
    0.24
     specifically
    0.24
     Notepad
    0.24
     whichever
    0.24
     only
    0.23
     Shortcut
    0.23
     Sticker
    0.23
     Printer
    0.23
     applicable
    0.23
    Activations Density 0.852%

    No Known Activations