© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129590
    Prev
    Next
    INDEX
    Explanations

    when during events

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

    The neuron strongly activates on numeric expressions—dates, times, years, and other number tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    嗉
    -1.45
    इटम
    -1.41
    麾
    -1.36
     acuarela
    -1.34
    losseum
    -1.33
    ichteten
    -1.31
    </b>
    -1.27
    不断的
    -1.23
    nase
    -1.23
    interprétation
    -1.23
    POSITIVE LOGITS
     when
    1.58
     unga
    1.53
     baumwolle
    1.48
    注意事
    1.48
    ྅
    1.41
     dieß
    1.37
    mäßige
    1.35
    ệu
    1.35
     花纹
    1.33
     素描
    1.33
    Activations Density 0.022%

    No Known Activations