© 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-65K
    7. 13631
    Prev
    Next
    INDEX
    Explanations

    conditional phrasing following if

    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
     concurrently
    0.57
    ڊ
    0.48
     natomiast
    0.47
    į
    0.46
     simultaneously
    0.46
     pertain
    0.43
     t
    0.42
    in
    0.40
     கல்வி
    0.40
     likewise
    0.40
    POSITIVE LOGITS
    庆祝
    0.51
    汉
    0.48
    满满
    0.46
    大约
    0.46
    报告
    0.45
    问题
    0.44
    回顾
    0.44
    Problems
    0.43
     sonrası
    0.43
     провести
    0.43
    Activations Density 0.012%

    No Known Activations