© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79400
    Prev
    Next
    INDEX
    Explanations

    legal or factual questions

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

    The neuron consistently activates on multi‐digit numeric tokens (i.e. standalone numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    gypti
    -1.02
    Mengapa
    -0.96
     by
    -0.96
     at
    -0.96
     or
    -0.94
    Bereich
    -0.94
     Considering
    -0.93
     when
    -0.93
     noteworthy
    -0.93
     during
    -0.91
    POSITIVE LOGITS
                    
    1.10
                 
    1.06
         
    1.05
    1.05
    0.99
                     
    0.99
                
    0.99
    なのでしょう
    0.98
              
    0.97
                            
    0.96
    Activations Density 0.056%

    No Known Activations