© 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. 116035
    Prev
    Next
    INDEX
    Explanations

    words followed by in

    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
     exportación
    -0.93
     untersucht
    -0.87
     démarrer
    -0.85
    btnNew
    -0.83
    安く
    -0.81
     contribuer
    -0.81
     energías
    -0.81
    に行って
    -0.81
     orientación
    -0.80
     там
    -0.79
    POSITIVE LOGITS
     in
    4.38
     In
    1.91
     în
    1.77
    in
    1.59
     isIn
    1.51
     σε
    1.44
    isIn
    1.43
    In
    1.43
     در
    1.41
    IsIn
    1.30
    Activations Density 0.165%

    No Known Activations