© 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. 66152
    Prev
    Next
    INDEX
    Explanations

    numerical time durations

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

    The neuron principally responds to numeric tokens (digits or multi‐digit 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
     year
    -0.96
     semic
    -0.77
     недель
    -0.76
    tiet
    -0.74
    妊
    -0.73
    セミ
    -0.73
     năm
    -0.73
    raga
    -0.71
     Framed
    -0.70
    umplimiento
    -0.70
    POSITIVE LOGITS
     two
    1.88
    two
    1.55
    Two
    1.43
    两个
    1.30
     Two
    1.28
    兩個
    1.27
     zwei
    1.17
     three
    1.17
     deux
    1.13
    TWO
    1.12
    Activations Density 0.050%

    No Known Activations