© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2262
    Prev
    Next
    INDEX
    Explanations

    Basque language

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

    Basque text and names

    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_53_width_65k_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
    ції
    0.50
     перший
    0.50
     vowed
    0.48
    翊
    0.48
     ві
    0.47
     всі
    0.46
     використа
    0.45
     क़
    0.45
    捆
    0.45
    柅
    0.44
    POSITIVE LOGITS
     eta
    1.06
     guzt
    1.04
     tx
    0.98
     izango
    0.97
     erab
    0.95
     edo
    0.88
     egiten
    0.88
    atzeko
    0.88
     Tx
    0.87
    tx
    0.86
    Activations Density 0.009%

    No Known Activations