© 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. 84249
    Prev
    Next
    INDEX
    Explanations

    Tennis, year, round, final, opening

    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
     work
    -1.05
     when
    -0.81
     even
    -0.79
     September
    -0.78
    工作
    -0.77
    데
    -0.77
    னர்
    -0.75
    ぜ
    -0.71
     during
    -0.70
     notare
    -0.69
    POSITIVE LOGITS
     groet
    0.93
     izay
    0.88
    Serbia
    0.87
     Serbia
    0.85
    킁
    0.82
    ごちそう
    0.82
     hindi
    0.81
     TextAlign
    0.81
    grids
    0.81
     terrific
    0.81
    Activations Density 0.001%

    No Known Activations