© 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. 11596
    Prev
    Next
    INDEX
    Explanations

    development/donkey foal

    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
     любую
    0.45
     アウト
    0.44
     любого
    0.43
     любой
    0.42
     ಯಾವುದ
    0.41
     любом
    0.41
    任何
    0.40
    р
    0.40
    푎
    0.40
    όν
    0.40
    POSITIVE LOGITS
     Life
    0.44
     conceptually
    0.39
     lifecycle
    0.38
     delightfully
    0.38
     Transform
    0.38
     fundamentally
    0.38
     subtly
    0.37
     life
    0.35
     intranet
    0.35
     subtle
    0.35
    Activations Density 0.120%

    No Known Activations