© 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. 50513
    Prev
    Next
    INDEX
    Explanations

    names of rivers

    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
     ujarnya
    -0.81
     jelasnya
    -0.79
    /{
    -0.75
     ungkapnya
    -0.74
    未完
    -0.71
     enamorado
    -0.70
     нашем
    -0.69
    紆
    -0.68
    Requisitos
    -0.68
     chế
    -0.68
    POSITIVE LOGITS
     River
    1.38
     rivers
    1.26
     river
    1.22
    River
    1.09
     tributaries
    1.09
     Río
    1.07
     Thames
    0.95
     tributary
    0.95
     río
    0.91
     نهر
    0.91
    Activations Density 0.094%

    No Known Activations