© 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. 71706
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years or months

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

    This neuron activates on numeric tokens, spotting numbers (like ages, percentages, measurements, and other statistics).

    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
    已经
    -1.14
    简介
    -1.10
    大多数
    -1.05
    짜
    -1.02
     calça
    -1.02
     POLIC
    -1.02
     ?
    -1.01
     آزم
    -0.99
     empez
    -0.99
    터
    -0.97
    POSITIVE LOGITS
    がありますが
    1.23
    <bos>
    1.18
    そういった
    1.13
     PUSTAKA
    1.05
    尔的
    1.02
    canActivate
    1.02
    alians
    1.02
    钳
    1.02
    crito
    1.02
    Aantal
    1.00
    Activations Density 0.001%

    No Known Activations