© 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. 40856
    Prev
    Next
    INDEX
    Explanations

    total cost or amount

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

    This neuron activates on occurrences of the word “total,” especially when it heads a numeric summary (e.g. “The total …”).

    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
    -1.93
                       
    -1.83
     &
    -1.83
     VERY
    -1.75
    两个
    -1.71
     //$
    -1.71
    大多数
    -1.70
    
    -1.68
     GOING
    -1.68
            
    -1.66
    POSITIVE LOGITS
     estekak
    1.86
    
    1.76
    endió
    1.70
     amount
    1.69
     innumerable
    1.67
     which
    1.63
     enticing
    1.63
     touted
    1.63
    おすすめの
    1.62
    seamnă
    1.62
    Activations Density 0.017%

    No Known Activations