© 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. 22-GEMMASCOPE-RES-131K
    7. 12885
    Prev
    Next
    INDEX
    Explanations

    code structure and imports

    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_22/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
    Ưu
    -1.04
    itism
    -1.02
    　→
    -1.00
    trường
    -0.99
    /
    -0.96
    Mereka
    -0.96
     estadía
    -0.94
     pengobatan
    -0.94
     quark
    -0.91
    kunjung
    -0.91
    POSITIVE LOGITS
     miesięcy
    1.11
     płasz
    1.02
     krás
    1.00
     Hinsicht
    0.95
     ندارد
    0.94
    asilkan
    0.93
    ：……
    0.91
     what
    0.91
    gebäude
    0.91
     łóż
    0.90
    Activations Density 0.020%

    No Known Activations