© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73064
    Prev
    Next
    INDEX
    Explanations

    Sanskrit names and terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to Indian proper names and terms—especially South Asian place names, temple or deity names, and historical figure names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.81
    0
    -1.61
    <td>
    -1.52
     The
    -1.49
     nebst
    -1.48
          
    -1.45
    ↵↵
    -1.41
    を使用した
    -1.41
            
    -1.40
                       
    -1.38
    POSITIVE LOGITS
    擧
    1.59
    　　*
    1.56
    At
    1.55
    ！"
    1.55
    ｋ
    1.55
    ılar
    1.52
    When
    1.52
    ห์
    1.51
    луйста
    1.50
     彼
    1.48
    Activations Density 0.015%

    No Known Activations