© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2332
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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_17_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
     Còn
    1.14
     ​​
    1.14
     ідэ
    1.14
     Ã
    1.13
     Dự
    1.11
     नाबाद
    1.08
     マルチ
    1.05
     ??
    1.05
     首
    1.03
     Geç
    1.03
    POSITIVE LOGITS
    4
    3.09
    3
    2.86
    5
    2.82
    6
    2.80
    2
    2.72
    ４
    2.70
    7
    2.68
    8
    2.61
    9
    2.55
    ５
    2.43
    Activations Density 0.362%

    No Known Activations