© 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. 22-GEMMASCOPE-RES-131K
    7. 72813
    Prev
    Next
    INDEX
    Explanations

    Sri followed by Lankan or Lanka

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

    The neuron fires on the honorific “Sri” when it appears in proper names (especially “Sri Lanka”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    鑁
    -2.72
    新たな
    -2.50
    却没有
    -2.45
    杁
    -2.38
     derzeit
    -2.17
     geladeira
    -2.14
     brinquedo
    -2.14
     botão
    -2.13
    也只是
    -2.13
     gebraucht
    -2.11
    POSITIVE LOGITS
    ра
    2.86
     vatten
    2.50
    et
    2.28
    
    2.22
     kredi
    2.22
    ного
    2.20
    i
    2.16
    瑧
    2.16
    脯
    2.06
     evidenced
    2.00
    Activations Density 0.004%

    No Known Activations