© 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. 47865
    Prev
    Next
    INDEX
    Explanations

    a vai / vou

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

    The neuron fires on words marking future tense (e.g. English “going to”/“will” and Portuguese “vai”/“irá”).

    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
    ’
    -2.61
    鴣
    -2.27
    for
    -2.22
    w
    -2.13
    it
    -2.11
    
    -2.11
     ambayo
    -2.09
     biß
    -2.06
    ﹶ
    -2.03
    䊐
    -1.96
    POSITIVE LOGITS
    </strong>
    2.16
     About
    1.77
     Both
    1.74
    很喜欢
    1.73
     我们
    1.73
     Like
    1.73
    感激
    1.73
     We
    1.71
     Personally
    1.70
     admirably
    1.69
    Activations Density 0.002%

    No Known Activations