© 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. 44835
    Prev
    Next
    INDEX
    Explanations

    before / and linguistic connectors

    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
    ก
    0.53
     dinero
    0.47
    추
    0.47
     paredes
    0.47
    ഡോ
    0.46
     tirelessly
    0.46
     regalos
    0.45
     crisp
    0.45
    OUGHT
    0.45
     courtship
    0.44
    POSITIVE LOGITS
     قبل
    0.57
     و
    0.56
     לפני
    0.51
     και
    0.51
     и
    0.50
     và
    0.46
    াসে
    0.46
     ו
    0.45
    与
    0.44
     before
    0.42
    Activations Density 0.000%

    No Known Activations