© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58032
    Prev
    Next
    INDEX
    Explanations

    lateinit and lazy initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     มัน
    -2.02
    极为
    -1.86
     It
    -1.84
     \
    -1.64
    ごちそう
    -1.63
     ถ้า
    -1.61
    来ました
    -1.60
    难过
    -1.60
        
    -1.59
    ры
    -1.59
    POSITIVE LOGITS
    i
    2.11
     vatten
    1.95
    as
    1.81
     that
    1.80
    b
    1.77
     lateinit
    1.73
    šov
    1.73
    ate
    1.73
     but
    1.71
    }$
    1.70
    Activations Density 0.001%

    No Known Activations