© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4372
    Prev
    Next
    INDEX
    Explanations

    legal case party opposition

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

    The neuron activates on multi‐digit numeric tokens (long sequences of digits).

    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
     on
    -0.92
     that
    -0.89
    tujuan
    -0.83
     may
    -0.82
     one
    -0.79
     any
    -0.77
    ֠
    -0.74
     had
    -0.74
    hamb
    -0.73
     data
    -0.71
    POSITIVE LOGITS
                            
    2.80
                                   
    2.63
                                
    2.58
                             
    2.55
                        
    2.53
                          
    2.52
                           
    2.42
                         
    2.41
                              
    2.41
                      
    2.38
    Activations Density 0.181%

    No Known Activations