© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72091
    Prev
    Next
    INDEX
    Explanations

    sports competitions and athletes

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

    The neuron fires strongly on terms related to competition and racing—words like “racing,” “competitive,” “competition,” “sport(s),” and “cars.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    会の
    -1.58
     new
    -1.56
    ?
    -1.55
    </tfoot>
    -1.52
    dersfield
    -1.46
     after
    -1.41
     Our
    -1.38
    眼前的
    -1.37
     will
    -1.36
     після
    -1.33
    POSITIVE LOGITS
    みなさん
    1.56
     gese
    1.48
    s
    1.41
     verhind
    1.38
     kampus
    1.37
     soste
    1.36
     acciaio
    1.35
     redonda
    1.30
     manquer
    1.30
     arrêter
    1.30
    Activations Density 0.053%

    No Known Activations