© 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. 6942
    Prev
    Next
    INDEX
    Explanations

    U words and abbreviations

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

    words starting with U

    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
    ע
    0.50
    ኪ
    0.42
    تن
    0.40
    Ό
    0.39
     умова
    0.39
    জনের
    0.39
    ک
    0.38
    tive
    0.37
    lance
    0.37
    高い
    0.36
    POSITIVE LOGITS
    rainian
    0.48
    arakhand
    0.46
    ்துறை
    0.46
    avasti
    0.46
    陋
    0.46
     UB
    0.45
    ARAJ
    0.45
    льтра
    0.44
    bilical
    0.44
    নৈতিক
    0.44
    Activations Density 0.200%

    No Known Activations