© 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. 59768
    Prev
    Next
    INDEX
    Explanations

    ouabain or outof

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

    This neuron detects the Portuguese word "ou" which means "or" in English.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is chiefly activated by the Romance‐language conjunction “ou” (i.e. “or”).

    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
    ],
    -2.81
    that
    -2.64
    ”,
    -2.56
     intentando
    -2.52
     можуть
    -2.48
    },
    -2.47
    ,”
    -2.42
     проблеми
    -2.34
    ’,
    -2.31
     gustaría
    -2.31
    POSITIVE LOGITS
    丏
    3.09
     "
    2.86
    퐸
    2.75
    婠
    2.73
    
    2.73
    ний
    2.72
     mauva
    2.64
    饜
    2.59
     serait
    2.58
     molti
    2.56
    Activations Density 0.001%

    No Known Activations