© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5641
    Prev
    Next
    INDEX
    Explanations

    followed by prepositions

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     często
    0.29
     []);
    0.28
     suivie
    0.27
     puis
    0.27
     („
    0.27
     كبير
    0.27
     seguido
    0.27
     _.
    0.27
     souvent
    0.26
     Hadoop
    0.26
    POSITIVE LOGITS
    withstanding
    0.25
    ेंडर
    0.25
    мат
    0.25
    чит
    0.25
    чному
    0.24
    フル
    0.24
    мата
    0.24
    ‌ర
    0.24
    ак
    0.24
    anthemum
    0.24
    Activations Density 0.222%

    No Known Activations