© 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. 47922
    Prev
    Next
    INDEX
    Explanations

    integer types

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

    This neuron activates on occurrences of the integer‐type keyword “Int.”

    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
    0
    -2.91
    Compared
    -2.70
      
    -2.63
    ,’
    -2.63
    Their
    -2.61
    ↵
    -2.59
    However
    -2.56
    They
    -2.55
     ‘’
    -2.52
     “
    -2.45
    POSITIVE LOGITS
     '
    3.55
    های
    2.95
    ?"
    2.64
    讴
    2.58
    ا
    2.58
     کردن
    2.39
     zewnętrzne
    2.36
    
    2.33
    ebenarnya
    2.33
     Interment
    2.31
    Activations Density 0.011%

    No Known Activations