© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    italian language and culture

    np_acts-logits-general · gemini-2.5-flash-lite

    Italy and Italian statistics

    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
     Джек
    0.54
    лл
    0.50
    VSLU
    0.50
    Ꭴ
    0.50
     Chipotle
    0.49
     эсеп
    0.49
    йдз
    0.49
    ෲ
    0.49
    ඈ
    0.48
    рю
    0.48
    POSITIVE LOGITS
     Italian
    1.31
    イタリア
    1.28
     italian
    1.27
     Repubblica
    1.25
    Italian
    1.24
     Scuola
    1.24
     Cagliari
    1.22
     Italy
    1.16
     Istituto
    1.16
     italiani
    1.16
    Activations Density 0.137%

    No Known Activations