© 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-262K
    7. 109587
    Prev
    Next
    INDEX
    Explanations

    describing data structures

    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
    Negative Logits
     necesitar
    0.54
    谔
    0.54
     فبراير
    0.52
     precisar
    0.50
     necesitamos
    0.50
    ÍN
    0.50
     क्वाड्र
    0.50
     ഇപ്പോൾ
    0.49
    ombasa
    0.48
    राष्ट्रपति
    0.47
    POSITIVE LOGITS
    ）
    0.43
     accru
    0.43
     The
    0.41
     This
    0.40
     hush
    0.39
     privacy
    0.38
    ’,
    0.38
     deems
    0.38
     They
    0.38
    隠
    0.37
    Activations Density 0.012%

    No Known Activations