© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15559
    Prev
    Next
    INDEX
    Explanations

    Copyright notices (e.g., All rights reserved)

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

    all / totality

    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_31_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
     వలన
    0.49
    舂
    0.44
    系统的
    0.42
    出来的
    0.42
    腧
    0.42
    いため
    0.41
     கடந்த
    0.41
     nField
    0.41
     лаборатор
    0.40
    ধার
    0.40
    POSITIVE LOGITS
     semua
    0.56
     todas
    0.55
     all
    0.52
     All
    0.51
     todos
    0.48
     всех
    0.46
    !
    0.45
     tutte
    0.43
     Inc
    0.43
     were
    0.42
    Activations Density 0.049%

    No Known Activations