© 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. 60363
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The neuron fires on numeric literal tokens (integer constants) in 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
     may
    -1.54
     maybe
    -1.27
     might
    -1.23
     people
    -1.02
     Maybe
    -1.01
     perhaps
    -0.99
     probably
    -0.98
     possibly
    -0.98
     Perhaps
    -0.94
     could
    -0.90
    POSITIVE LOGITS
     upvotes
    0.99
                    
    0.98
                        
    0.98
    劇場
    0.94
    jednoc
    0.89
     아니라
    0.89
                            
    0.88
    )?;
    0.88
     grati
    0.86
     ?>>
    0.86
    Activations Density 0.035%

    No Known Activations