© 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. 7302
    Prev
    Next
    INDEX
    Explanations

    numbers and periods

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

    The neuron flags numeric expressions—tokens representing digits, years, percentages, and other number‐related data.

    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
    驚く
    -0.91
     idéia
    -0.90
    なくなって
    -0.89
    不愿意
    -0.88
    不明白
    -0.88
     utilisent
    -0.85
     whereby
    -0.85
    OnError
    -0.84
    加大
    -0.84
    更改
    -0.84
    POSITIVE LOGITS
    ارك
    0.83
     epile
    0.81
    lasse
    0.80
    城
    0.80
    安心
    0.79
     nochmal
    0.79
    первых
    0.79
    合成
    0.78
     мне
    0.77
    考古
    0.77
    Activations Density 0.014%

    No Known Activations