© 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. 103518
    Prev
    Next
    INDEX
    Explanations

    Ghanaian educational and social institutions

    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
    進行
    -0.78
     グループ
    -0.75
     オーバー
    -0.73
     graduación
    -0.73
    (!(
    -0.72
    恢復
    -0.71
    Doubles
    -0.71
     buttons
    -0.71
    toma
    -0.69
    containers
    -0.69
    POSITIVE LOGITS
    UKU
    0.85
     SKU
    0.77
    ENTOS
    0.75
     Pence
    0.75
    ordum
    0.74
    pkl
    0.71
    hiro
    0.71
     Xi
    0.71
     néanmoins
    0.71
    UKA
    0.70
    Activations Density 0.010%

    No Known Activations