© 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. 38657
    Prev
    Next
    INDEX
    Explanations

    baseball fields games

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    yung
    -0.84
     الجهاز
    -0.77
     Yung
    -0.75
    Unsigned
    -0.72
     destitute
    -0.72
     techs
    -0.71
     pact
    -0.71
     technicians
    -0.71
    permitAll
    -0.71
    öv
    -0.70
    POSITIVE LOGITS
     baseball
    1.96
    baseball
    1.78
    Baseball
    1.51
     Baseball
    1.41
    ⚾
    1.31
     Babe
    1.17
     野球
    1.15
    野球
    1.13
     béisbol
    1.10
     umpire
    1.09
    Activations Density 0.034%

    No Known Activations