© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102464
    Prev
    Next
    INDEX
    Explanations

    examples after "include"

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

    the neuron detects list-introducing or example-introducing discourse markers (e.g. “features,” “include,” “examples,” “questions”).

    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
     
    -1.75
     of
    -1.70
    in
    -1.70
     with
    -1.60
       
    -1.55
                        
    -1.55
     "--
    -1.50
     In
    -1.48
            
    -1.48
    All
    -1.47
    POSITIVE LOGITS
    秶
    1.92
    ٧
    1.91
    を使用した
    1.85
     کردند
    1.84
    
    1.82
     anniversaire
    1.79
    ⇹
    1.77
     pérd
    1.77
     -¿
    1.77
    ⩤
    1.73
    Activations Density 0.024%

    No Known Activations