© 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. 73729
    Prev
    Next
    INDEX
    Explanations

    extending through time periods

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

    The neuron specializes in spotting numeric or quantifying expressions (years, centuries, counts, and other number-related tokens).

    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
     different
    -0.93
     разные
    -0.93
     diferentes
    -0.84
    collect
    -0.84
    也會
    -0.81
    大部分
    -0.81
     dve
    -0.80
    の山
    -0.79
    はん
    -0.79
     going
    -0.78
    POSITIVE LOGITS
     where
    1.22
    חים
    0.99
    Beyond
    0.96
     into
    0.95
     inclui
    0.94
    ipfel
    0.94
    IFYING
    0.93
    koła
    0.92
     =-\
    0.91
     ámbito
    0.91
    Activations Density 0.070%

    No Known Activations