© 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. 23473
    Prev
    Next
    INDEX
    Explanations

    footballer, coach, or player titles

    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
     ريا
    -0.81
    raseña
    -0.79
     esternos
    -0.78
    getItemId
    -0.78
    mologie
    -0.77
    resizeMode
    -0.75
     Brexit
    -0.73
     ];
    -0.71
     basketball
    -0.71
     todavía
    -0.71
    POSITIVE LOGITS
     isang
    0.86
     Distillery
    0.81
    　
    0.80
     Aa
    0.79
    manic
    0.78
    実
    0.78
     Yugoslav
    0.78
    這裡
    0.76
     beh
    0.75
     Yugos
    0.75
    Activations Density 0.109%

    No Known Activations