© 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. 10-GEMMASCOPE-RES-131K
    7. 123556
    Prev
    Next
    INDEX
    Explanations

    sequences of zeros

    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_10/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
    
    -1.84
    ᑯ
    -1.81
     Nuevas
    -1.79
     schuldig
    -1.77
     its
    -1.73
     parfü
    -1.71
     pomaga
    -1.70
     guapos
    -1.68
     allerlei
    -1.68
     diverses
    -1.68
    POSITIVE LOGITS
     =
    1.78
     usually
    1.68
     there
    1.63
     began
    1.61
    از
    1.57
     (
    1.56
     also
    1.54
    )";
    1.52
     first
    1.51
     ((
    1.50
    Activations Density 0.078%

    No Known Activations