© 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. 61241
    Prev
    Next
    INDEX
    Explanations

    yards gained in sports

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

    The neuron detects numerical yardage figures (numbers and the word “yard”/“yards”) in football contexts.

    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
    </h2>
    -1.73
    罴
    -1.55
    臜
    -1.54
     разных
    -1.45
     mismas
    -1.44
    ⑊
    -1.41
     definitiv
    -1.41
    
    -1.38
     ſch
    -1.35
     strukt
    -1.34
    POSITIVE LOGITS
     from
    2.19
     add
    1.61
     including
    1.53
     with
    1.51
     культура
    1.41
    𝗼
    1.34
     serdecznie
    1.34
     ensuring
    1.32
     that
    1.31
     because
    1.31
    Activations Density 0.020%

    No Known Activations