© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10281
    Prev
    Next
    INDEX
    Explanations

    if clauses and subsequent actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.33
    。
    0.29
     vostre
    0.27
    人们
    0.26
     lewat
    0.26
     avevo
    0.26
     людей
    0.26
     villes
    0.25
     minhas
    0.25
     સં
    0.25
    POSITIVE LOGITS
    那么
    0.37
    则
    0.34
    則
    0.33
    那就
    0.33
    那麼
    0.32
    它可以
    0.31
     则
    0.29
    then
    0.28
     ಅದನ್ನು
    0.28
    而且
    0.28
    Activations Density 0.088%

    No Known Activations