© 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. 81449
    Prev
    Next
    INDEX
    Explanations

    sports draft and player signing

    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
     låg
    -0.82
     ボ
    -0.82
     Visitation
    -0.81
     liefern
    -0.74
     selv
    -0.74
    caccio
    -0.73
    icordia
    -0.73
    onPause
    -0.72
    erapa
    -0.72
     linkovi
    -0.71
    POSITIVE LOGITS
     auction
    1.27
     draft
    1.13
     marquee
    1.06
     salary
    1.05
     foreign
    1.02
    draft
    0.97
     retained
    0.96
    foreign
    0.95
     signing
    0.93
     foreigner
    0.93
    Activations Density 0.019%

    No Known Activations