© 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. 92555
    Prev
    Next
    INDEX
    Explanations

    instructor resources, free samples, book orders

    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
     newspaper
    -0.90
     veröffentlich
    -0.84
     словарь
    -0.79
     PLWABN
    -0.77
    是一個
    -0.77
     empfangen
    -0.76
     limon
    -0.75
    ombs
    -0.75
     dunklen
    -0.74
     RCS
    -0.73
    POSITIVE LOGITS
     book
    1.14
    ordered
    1.12
    ordering
    1.02
     titles
    1.01
    isbn
    0.97
     INSPECTION
    0.96
    Orders
    0.96
     preorder
    0.96
    Praise
    0.95
     bestellen
    0.95
    Activations Density 0.077%

    No Known Activations