© 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. 109599
    Prev
    Next
    INDEX
    Explanations

    American Idol contestants and Miranda Kerr

    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
    тивні
    -0.85
    ộp
    -0.81
    "./
    -0.79
     banker
    -0.77
     اداری
    -0.77
    ровке
    -0.74
     FIBA
    -0.74
    ())),
    -0.71
    expandindo
    -0.71
     sectarian
    -0.71
    POSITIVE LOGITS
     Idol
    1.49
    idol
    0.96
     contestants
    0.95
     audition
    0.86
     contestant
    0.86
     dawg
    0.82
     idol
    0.81
     конкурс
    0.79
    optimis
    0.78
    Id
    0.77
    Activations Density 0.017%

    No Known Activations