© 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-16K
    7. 6395
    Prev
    Next
    INDEX
    Explanations

    Narendra Modi and India

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ichung
    0.47
     left
    0.45
    ilted
    0.40
    左
    0.40
    mid
    0.40
     *}(
    0.39
    否
    0.39
    ży
    0.39
    instellung
    0.39
     ylabel
    0.38
    POSITIVE LOGITS
     मोदी
    0.56
    मोदी
    0.49
     பிரதமர்
    0.48
     મોદી
    0.48
    প্রধানমন্ত্রী
    0.48
     туристи
    0.47
     బీజేపీ
    0.45
     관광
    0.45
     pledges
    0.44
     সমাবেশে
    0.43
    Activations Density 0.063%

    No Known Activations