© 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. 67059
    Prev
    Next
    INDEX
    Explanations

    numbers or proper nouns

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

    This neuron detects numeric expressions (numbers, dates, percentages, and other digit‐based tokens).

    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
    ώ
    -1.53
     you
    -1.46
     paramInt
    -1.45
     use
    -1.45
    mathrm
    -1.38
                
    -1.37
     tendrás
    -1.35
         
    -1.35
    weightedMode
    -1.34
           
    -1.34
    POSITIVE LOGITS
     incrí
    1.30
     maksi
    1.29
    鉋
    1.27
     inconce
    1.27
    Далее
    1.25
     commencent
    1.23
    ௅
    1.22
     indescri
    1.21
    смартфон
    1.21
     investir
    1.20
    Activations Density 0.622%

    No Known Activations