© 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. 34-GEMMASCOPE-RES-131K
    7. 98399
    Prev
    Next
    INDEX
    Explanations

    starting pitcher names

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

    The neuron is especially sensitive to mentions of baseball–style proper names (teams, players, and related game entities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Players
    -0.88
     players
    -0.79
    jestic
    -0.77
    ACTOR
    -0.73
     breeds
    -0.72
    jois
    -0.71
    strando
    -0.71
    abba
    -0.69
    Nº
    -0.69
     sunglasses
    -0.69
    POSITIVE LOGITS
     starter
    1.38
    starter
    1.09
    Starter
    1.04
     Starter
    1.03
     starting
    0.90
     getStart
    0.81
    setStart
    0.77
     lef
    0.77
     स्टार
    0.77
     staff
    0.76
    Activations Density 0.027%

    No Known Activations