© 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. 115798
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or ordinals

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

    The neuron consistently activates on standalone numeric tokens (e.g. multi-digit numbers and years).

    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
     ३
    -1.10
    があります
    -1.09
    。。。。
    -1.06
    ！！！！！
    -1.05
    よろしくお願いいたします
    -1.03
    ätigung
    -1.02
    や
    -1.02
    世間
    -1.01
    兩個
    -1.00
     Beberapa
    -1.00
    POSITIVE LOGITS
    0
    1.31
     forskellige
    1.05
    っているので
    1.05
    <>
    1.02
     verschillende
    0.99
     erila
    0.97
    為に
    0.97
     különböző
    0.97
    になってしまう
    0.96
    際には
    0.95
    Activations Density 0.164%

    No Known Activations