© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11625
    Prev
    Next
    INDEX
    Explanations

    what is or was

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

    what follows

    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_40_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
     overlooked
    0.45
     ایسا
    0.41
     did
    0.41
     does
    0.40
     do
    0.40
     changed
    0.40
     хуже
    0.39
     «
    0.39
     Does
    0.39
     jejich
    0.38
    POSITIVE LOGITS
     Đình
    0.55
    俨
    0.51
     считаю
    0.45
     pudi
    0.45
    狛
    0.44
     purported
    0.43
    ungeons
    0.43
     Đường
    0.42
    اسي
    0.41
    ليس
    0.41
    Activations Density 0.137%

    No Known Activations