© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36408
    Prev
    Next
    INDEX
    Explanations

    copy constructor or move constructor

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urnya
    -1.09
     дополнительные
    -1.06
    nows
    -1.02
     поддержка
    -0.99
     ciem
    -0.99
     پشتیبانی
    -0.98
     trabaja
    -0.97
    ntilde
    -0.96
    nol
    -0.95
     crear
    -0.94
    POSITIVE LOGITS
     preceded
    0.92
     plastico
    0.91
     karl
    0.91
    䨻
    0.90
     rapido
    0.90
     kamar
    0.89
     kazak
    0.89
     lyder
    0.89
     Marzo
    0.88
    wnątrz
    0.88
    Activations Density 0.007%

    No Known Activations