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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11728
    Prev
    Next
    INDEX
    Explanations

    Oy, Oi, Oyster, analgesics

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

    The neuron activates for the word "Oy" and variations like "Oyster" with higher activation for the exact word "Oy".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ୌ
    -3.42
    Ꮵ
    -2.86
    棪
    -2.77
    erintah
    -2.75
     הם
    -2.72
     jsi
    -2.70
    。
    -2.69
     opro
    -2.69
    </sup>
    -2.67
     zni
    -2.64
    POSITIVE LOGITS
    ↵↵
    3.50
    ly
    2.55
    но
    2.45
     –
    2.44
    –
    2.36
     將
    2.19
     
    2.17
    -
    2.13
     evidenced
    2.09
    躄
    2.09
    Activations Density 0.009%

    No Known Activations