© 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. 83947
    Prev
    Next
    INDEX
    Explanations

    Spanish questions mark

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

    The neuron activates on the inverted question-mark character “¿,” indicating it detects the start of a Spanish question.

    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
     Those
    -2.73
    D
    -2.55
    f
    -2.53
    k
    -2.53
    m
    -2.48
    h
    -2.48
    𖥦
    -2.47
     unrelenting
    -2.38
     unwavering
    -2.38
     Generally
    -2.38
    POSITIVE LOGITS
    {
    2.80
    埽
    2.58
    
    2.50
    苤
    2.30
     ライト
    2.25
    甞
    2.23
    坶
    2.23
     centaines
    2.23
     startling
    2.19
    creating
    2.16
    Activations Density 0.001%

    No Known Activations