© 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. 89948
    Prev
    Next
    INDEX
    Explanations

    chronological or sorted lists

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

    The neuron activates on numeric tokens (numbers) 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_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
     উ
    -0.72
    コモ
    -0.68
    侷
    -0.68
    ≀
    -0.67
    危險
    -0.67
    onsumsi
    -0.66
    Multivariate
    -0.66
     জন
    -0.66
    ření
    -0.65
     Standardi
    -0.65
    POSITIVE LOGITS
     chronological
    5.25
    chron
    4.28
     chronologically
    4.13
    Chron
    3.97
     Chron
    3.89
     chronology
    3.77
     chron
    3.70
     хро
    3.09
     Chronology
    3.02
     CHRON
    2.91
    Activations Density 0.088%

    No Known Activations