© 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. 22-GEMMASCOPE-RES-131K
    7. 68862
    Prev
    Next
    INDEX
    Explanations

    professional teams

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

    The main thing this neuron does is detect occurrences of the word “team.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     different
    -1.57
     gefördert
    -1.54
     following
    -1.45
     anerkannt
    -1.45
    不同
    -1.44
     berbeda
    -1.41
     gemeinsamen
    -1.33
     erfolgreichen
    -1.31
     einzigartigen
    -1.30
     use
    -1.30
    POSITIVE LOGITS
     of
    2.30
     who
    1.47
     тот
    1.39
     שלנו
    1.30
     Мексика
    1.30
    bolistas
    1.29
    чно
    1.29
     работает
    1.28
     composto
    1.28
    žas
    1.27
    Activations Density 0.017%

    No Known Activations