© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1551
    Prev
    Next
    INDEX
    Explanations

    code structure and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     reconsider
    0.96
    benchmark
    0.94
    ({...
    0.89
    catalyzed
    0.88
     PLUS
    0.88
    ​​
    0.87
     ‪
    0.86
    ​
    0.86
     образ
    0.85
    ️
    0.84
    POSITIVE LOGITS
     pilih
    1.48
     juga
    1.46
     tidak
    1.45
     بھی
    1.40
     tersedia
    1.39
     kecil
    1.39
     diberikan
    1.39
     refiere
    1.39
     jumlah
    1.38
     warga
    1.36
    Activations Density 0.306%

    No Known Activations