© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69646
    Prev
    Next
    INDEX
    Explanations

    speed skater

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

    The neuron fires on words related to skating—especially speed skating events, skaters, rinks, and related terminology.

    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
     móg
    -1.35
     変更
    -1.32
    .”)
    -1.28
     przycis
    -1.26
     drzwi
    -1.25
     spiaggia
    -1.23
     lunghezza
    -1.23
    velyn
    -1.22
    ”)
    -1.21
    
    -1.20
    POSITIVE LOGITS
    QPalette
    1.24
     rink
    1.22
    </h2>
    1.20
     for
    1.16
     و
    1.13
    !!
    1.13
    𝐅
    1.13
    、
    1.12
    anstalt
    1.11
    。
    1.11
    Activations Density 0.033%

    No Known Activations