© 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. 54086
    Prev
    Next
    INDEX
    Explanations

    Königsberg Prussia Kant

    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
     Niall
    -0.77
    haltens
    -0.76
     termen
    -0.73
    斑
    -0.72
    gården
    -0.71
     Grüsse
    -0.71
    edance
    -0.71
     vícti
    -0.69
    mässig
    -0.69
    骡
    -0.68
    POSITIVE LOGITS
     Kant
    1.87
    Kant
    1.64
     Immanuel
    1.33
     Critique
    1.29
     Nou
    1.02
     Schiller
    1.00
     nou
    0.98
     Prussian
    0.95
    Critique
    0.94
     kant
    0.93
    Activations Density 0.017%

    No Known Activations