© 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. 42731
    Prev
    Next
    INDEX
    Explanations

    sports

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

    The neuron activates on occurrences of the word “sport” (including “sports”).

    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
     
    -1.91
     "
    -1.54
    diseases
    -1.36
    \
    -1.34
     inven
    -1.34
    writeFile
    -1.32
     Munic
    -1.30
    锨
    -1.30
    {...
    -1.30
     elog
    -1.28
    POSITIVE LOGITS
    and
    2.14
     și
    1.79
     και
    1.68
    _
    1.63
     which
    1.59
    x
    1.52
     umie
    1.52
     verkau
    1.51
    vané
    1.51
    the
    1.51
    Activations Density 0.017%

    No Known Activations