© 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. 10-GEMMASCOPE-RES-131K
    7. 11579
    Prev
    Next
    INDEX
    Explanations

    Wisconsin, David, Rays, After, United, Seeds, All

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

    This neuron activates on numeric tokens (scores, statistics, and other numbers) in sports recaps.

    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
     lámparas
    -1.82
    inWeight
    -1.76
     and
    -1.73
     impresionantes
    -1.73
     why
    -1.71
     titolata
    -1.71
    irability
    -1.70
    sometimes
    -1.69
     αλλά
    -1.64
    etCode
    -1.64
    POSITIVE LOGITS
     was
    1.52
     all
    1.51
     at
    1.51
     didn
    1.48
    Ито
    1.41
    u
    1.38
     f
    1.34
    -
    1.33
    ne
    1.32
    Недостатки
    1.31
    Activations Density 0.025%

    No Known Activations