© 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. 45605
    Prev
    Next
    INDEX
    Explanations

    one year anniversary

    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
     almost
    -1.12
     nearly
    -1.09
     few
    -1.09
     some
    -1.06
     even
    -1.01
     около
    -1.01
     not
    -0.99
     unos
    -0.99
     maybe
    -0.95
     dozens
    -0.95
    POSITIVE LOGITS
     one
    4.94
    One
    2.86
     One
    2.69
    one
    2.58
     één
    2.56
    หนึ่ง
    2.48
     один
    2.44
     jednu
    2.13
     jednej
    2.13
     одну
    2.13
    Activations Density 0.172%

    No Known Activations