© 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. 11679
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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
    ۆ
    0.50
     dynamism
    0.47
    すすめ
    0.44
     և
    0.43
    არა
    0.43
     질문
    0.42
    ieli
    0.42
    ਵਾਈ
    0.42
     vectorial
    0.41
    ਾਰ
    0.41
    POSITIVE LOGITS
    aol
    0.54
    Horn
    0.48
     Everglades
    0.47
    N
    0.46
    on
    0.46
     Австра
    0.46
     Sutherland
    0.45
     αρκε
    0.45
     подобные
    0.45
     অস্ট্রেল
    0.44
    Activations Density 0.000%

    No Known Activations