© 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. 25703
    Prev
    Next
    INDEX
    Explanations

    every applicable item

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

    The neuron is detecting strong universal-quantifier language—especially the word “every.”

    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
    
    -1.58
     vários
    -1.55
     enormes
    -1.54
     hebben
    -1.46
     RBIs
    -1.44
     {?}
    -1.34
     certains
    -1.34
    某些
    -1.33
    uride
    -1.33
     enorme
    -1.32
    POSITIVE LOGITS
     every
    2.28
    Every
    2.16
     one
    2.14
     conceivable
    2.05
     Every
    1.97
     available
    1.79
     imaginable
    1.68
     possible
    1.66
     other
    1.49
    every
    1.48
    Activations Density 0.027%

    No Known Activations