© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12958
    Prev
    Next
    INDEX
    Explanations

    explanation, definition, summary

    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
    持续
    0.38
     Montréal
    0.38
     BBQ
    0.37
     Montreal
    0.37
     Adventure
    0.37
     ACA
    0.36
     Mont
    0.35
     ৪
    0.35
     Core
    0.35
     BTC
    0.35
    POSITIVE LOGITS
    也就是说
    0.51
    所謂
    0.40
     sogen
    0.40
    つまり
    0.40
    nilai
    0.39
    所谓
    0.39
     بنابراین
    0.39
    یعنی
    0.38
    funny
    0.37
    Consequently
    0.37
    Activations Density 0.161%

    No Known Activations