© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90649
    Prev
    Next
    INDEX
    Explanations

    Newark Athlete

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

    This neuron detects Spanish comparative quantifiers (e.g. “más” or “menos”).

    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
    圌
    -2.75
    鲧
    -2.66
    鴬
    -2.52
    
    -2.45
     Perſ
    -2.44
    みたら
    -2.38
    莇
    -2.34
    𝐲
    -2.33
     думал
    -2.33
    腠
    -2.31
    POSITIVE LOGITS
     más
    2.30
    Another
    2.17
     twor
    2.16
     immeasurable
    2.11
    With
    2.09
    You
    2.09
     neue
    2.09
     exacting
    2.08
     beckon
    2.08
     adorable
    2.06
    Activations Density 0.000%

    No Known Activations