© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59571
    Prev
    Next
    INDEX
    Explanations

    Major League Baseball

    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
     使っ
    -0.84
     kierow
    -0.81
    aided
    -0.79
    桶
    -0.78
     клави
    -0.78
    菖
    -0.77
     ngay
    -0.76
    によ
    -0.76
    DEZ
    -0.75
     главный
    -0.75
    POSITIVE LOGITS
    itarian
    1.23
    iteten
    1.20
     domo
    1.16
    tą
    1.13
    Major
    1.12
    major
    1.11
     league
    1.09
    itary
    1.08
     histo
    1.04
    minor
    1.00
    Activations Density 0.019%

    No Known Activations