© 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. 70067
    Prev
    Next
    INDEX
    Explanations

    alternatives connected by or

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

    The neuron responds specifically to the conjunction “or.”

    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
    {
    -2.05
    就没
    -1.96
     anunció
    -1.91
     REALLY
    -1.87
    就很
    -1.81
    泚
    -1.77
    쨩
    -1.73
     แ
    -1.72
    
    -1.69
     YEAR
    -1.63
    POSITIVE LOGITS
     one
    2.38
     as
    2.27
     of
    2.20
     what
    2.14
     find
    2.02
    
    2.00
     create
    1.97
     increase
    1.95
     remove
    1.90
     greatly
    1.89
    Activations Density 0.080%

    No Known Activations