© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59493
    Prev
    Next
    INDEX
    Explanations

    programming code and other languages

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

    The neuron detects numeric literals (integer constants) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ↵↵
    -1.34
    Ayr
    -0.82
     rather
    -0.79
    Kanal
    -0.78
    之下
    -0.77
    '];
    -0.76
     البته
    -0.75
    Buna
    -0.75
    ず
    -0.74
    ↵↵↵
    -0.73
    POSITIVE LOGITS
                
    1.31
     depending
    1.23
                    
    1.16
            
    1.15
     même
    1.13
     especially
    1.04
                            
    1.03
                 
    1.03
              
    1.02
     szczególnie
    1.02
    Activations Density 0.031%

    No Known Activations