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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27069
    Prev
    Next
    INDEX
    Explanations

    Lionel Messi and Argentina

    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
    碟
    0.47
    双
    0.40
    ロック
    0.39
     டை
    0.39
     টাই
    0.38
     W
    0.38
    犯
    0.38
     VALUES
    0.37
    票
    0.37
    CDS
    0.37
    POSITIVE LOGITS
    Buenos
    0.51
    Argentina
    0.48
     Argentina
    0.46
    ည်း
    0.46
     Buenos
    0.46
     guava
    0.46
     terutama
    0.45
     argent
    0.44
     argentino
    0.43
     আর্জেন্ট
    0.42
    Activations Density 0.012%

    No Known Activations