© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22887
    Prev
    Next
    INDEX
    Explanations

    same, mesmo, mismo

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

    The neuron fires on the Portuguese demonstrative “mesmo” (and its inflected forms like “mesma”), i.e. occurrences of the word meaning “same.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    )
    -3.02
    ,"
    -2.78
    I
    -2.77
    {
    -2.75
     '
    -2.67
    ]
    -2.56
    --
    -2.55
     need
    -2.47
    -2.22
    },
    -2.16
    POSITIVE LOGITS
    
    3.05
    ℣
    2.70
     alamu
    2.66
    鹟
    2.56
    ቾ
    2.45
    淠
    2.44
    ꯹
    2.42
    茑
    2.41
    égio
    2.36
    鸫
    2.30
    Activations Density 0.001%

    No Known Activations