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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    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

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    範
    0.48
    ASSIGN
    0.45
    碟
    0.43
     FINANCIAL
    0.43
    考核
    0.41
    ロック
    0.41
     roster
    0.41
    票
    0.40
    犯
    0.40
     টাই
    0.40
    POSITIVE LOGITS
    Buenos
    0.53
     Buenos
    0.53
    ည်း
    0.52
    Argentina
    0.46
    ormap
    0.44
     আর্জেন্ট
    0.44
     آئ
    0.43
     Argent
    0.43
     Argentine
    0.43
     guava
    0.42
    Activations Density 0.006%

    No Known Activations