© 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. 86992
    Prev
    Next
    INDEX
    Explanations

    baseball games, players, and terms

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

    The neuron detects mentions of the word “baseball.”

    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
    2
    -3.23
    \
    -3.16
     --
    -3.05
    /
    -3.00
     ('
    -2.98
    潆
    -2.91
     '
    -2.84
     "
    -2.83
     ---
    -2.81
    ?"
    -2.80
    POSITIVE LOGITS
    屺
    3.28
    ⸰
    3.03
    㐂
    2.97
    Ꮂ
    2.97
     poniendo
    2.89
    疍
    2.83
    ༆
    2.78
    刳
    2.72
    鮓
    2.69
     wody
    2.66
    Activations Density 0.006%

    No Known Activations