© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129016
    Prev
    Next
    INDEX
    Explanations

    Steelers, Nottingham, Julius

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

    The neuron fires strongly on capitalized proper names—especially sports team names like “Steelers.”

    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
    岽
    -2.89
    ing
    -2.63
    猡
    -2.53
    筏
    -2.52
    ة
    -2.50
    蔼
    -2.47
    赝
    -2.47
    苹
    -2.44
     哪
    -2.42
    砧
    -2.42
    POSITIVE LOGITS
    1
    3.66
    0
    2.94
    the
    2.88
    м
    2.83
    ?”
    2.78
     два
    2.73
    9
    2.63
    ーーーー
    2.63
    What
    2.61
    感じで
    2.55
    Activations Density 0.004%

    No Known Activations