© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58795
    Prev
    Next
    INDEX
    Explanations

    international tournaments and events

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

    The neuron is strongly detecting numeric expressions (dates, scores, quantities, monetary amounts, and other 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_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
     then
    -1.51
     further
    -1.39
     vedo
    -1.30
     bosco
    -1.24
     how
    -1.23
    也有
    -1.20
     farmaco
    -1.20
     corresponding
    -1.19
    </strong>
    -1.17
    クル
    -1.17
    POSITIVE LOGITS
     vooraf
    1.22
    ītā
    1.19
     opgenomen
    1.16
    蛰
    1.16
     wereld
    1.16
     nourriture
    1.13
    Sevilla
    1.12
    leriyle
    1.11
    Bigr
    1.09
    WIFI
    1.08
    Activations Density 0.074%

    No Known Activations