© 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. 108
    Prev
    Next
    INDEX
    Explanations

    because / for / since

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

    examples, illustrations

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

    sentence endings

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    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
    然后
    0.25
    然後
    0.25
     然後
    0.25
    Then
    0.25
    然后在
    0.24
     dann
    0.23
     then
    0.22
     затем
    0.22
    lds
    0.22
     następnie
    0.22
    POSITIVE LOGITS
     bowiem
    0.30
     কেননা
    0.30
     زیرا
    0.30
     totiž
    0.30
     ибо
    0.30
     오히려
    0.30
     deoarece
    0.29
     ведь
    0.29
     gdyż
    0.29
     hiszen
    0.28
    Activations Density 2.145%

    No Known Activations