© 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. 10-GEMMASCOPE-RES-131K
    7. 13562
    Prev
    Next
    INDEX
    Explanations

    uint data types

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

    The neuron strongly activates on numeric literals (number tokens) 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_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
     it
    -2.38
    uint
    -2.16
     and
    -1.94
    ;
    -1.63
     觀
    -1.62
    あっという間に
    -1.62
    Bukan
    -1.60
    垕
    -1.58
    不已
    -1.58
     часу
    -1.56
    POSITIVE LOGITS
    ↵↵
    1.96
                        
    1.95
                     
    1.91
    ཽ
    1.91
            
    1.91
        
    1.91
    genodigd
    1.89
    ℣
    1.89
               
    1.88
     uint
    1.88
    Activations Density 0.002%

    No Known Activations