© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14336
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in ,cially or ,ically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    𝗴
    0.41
    কাজ
    0.40
    वाहिक
    0.39
     bonnes
    0.39
    变成
    0.38
     comenc
    0.38
     pakai
    0.37
    浼
    0.37
    льнявыя
    0.37
     noix
    0.37
    POSITIVE LOGITS
    ,
    0.49
    ،
    0.45
    ut
    0.43
    ¸
    0.39
    ó
    0.38
    ore
    0.38
    utom
    0.38
    ，《
    0.38
    oz
    0.37
    ,*
    0.36
    Activations Density 0.148%

    No Known Activations