© 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. 10-GEMMASCOPE-RES-131K
    7. 9195
    Prev
    Next
    INDEX
    Explanations

    interval between times

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

    The neuron activates on numeric expressions that specify intervals (often time gaps) introduced by “between.”

    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
    {
    -2.25
     
    -1.98
    ,
    -1.95
    過ごす
    -1.64
    ’,
    -1.63
     time
    -1.59
     

    -1.59
                               
    -1.58
            
    -1.57
      
    -1.55
    POSITIVE LOGITS
    嗵
    2.23
    Ruju
    1.81
     作り方
    1.74
     anhänger
    1.73
     yako
    1.73
    豋
    1.72
     opérés
    1.72
    klere
    1.70
     třeba
    1.69
     增
    1.65
    Activations Density 0.019%

    No Known Activations