© 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. 7604
    Prev
    Next
    INDEX
    Explanations

    array access with comparisons

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

    The neuron detects integer numeric literals (sequences of digits) in code or text.

    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
    羮
    -2.69
    鰱
    -2.58
    
    -2.45
     mawar
    -2.45
    
    -2.41
     レスト
    -2.38
    朥
    -2.31
    
    -2.28
     墊
    -2.28
     them
    -2.28
    POSITIVE LOGITS
     they
    3.36
    あるいは
    2.41
          
    2.23
    高清
    2.20
      
    2.14
     sería
    2.09
     not
    2.08
     může
    2.06
     diseñ
    2.05
    。　　
    2.03
    Activations Density 0.005%

    No Known Activations