© 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. 37955
    Prev
    Next
    INDEX
    Explanations

    old english and medieval literature

    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
    loaded
    -0.81
     nada
    -0.78
     банков
    -0.77
     recuerdos
    -0.75
     паль
    -0.73
     unter
    -0.71
     loaded
    -0.71
     Spiro
    -0.69
     Hintergrund
    -0.69
    荤
    -0.69
    POSITIVE LOGITS
     Chaucer
    1.26
     Middle
    1.15
     English
    1.04
     England
    1.03
     medieval
    1.02
    MIDDLE
    0.95
    Middle
    0.93
    Chau
    0.93
     Beowulf
    0.93
     our
    0.87
    Activations Density 0.021%

    No Known Activations