© 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. 22-GEMMASCOPE-RES-131K
    7. 93023
    Prev
    Next
    INDEX
    Explanations

    past events and their completions

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

    The neuron responds to numeric tokens—years, measurements, and other numbers appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    люс
    -1.07
     valamint
    -1.06
     mereka
    -1.06
    
    -1.04
     will
    -1.02
     so
    -1.01
     might
    -1.01
    Nuevas
    -0.99
     can
    -0.98
     may
    -0.98
    POSITIVE LOGITS
     then
    2.55
     thereafter
    1.96
     subsequent
    1.80
     later
    1.73
     сразу
    1.59
     سپس
    1.59
    那时
    1.48
     тогда
    1.46
    then
    1.43
     immediately
    1.43
    Activations Density 0.214%

    No Known Activations