© 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. 102985
    Prev
    Next
    INDEX
    Explanations

    \documentclass

    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
     around
    -1.01
     either
    -0.93
     those
    -0.88
     oauth
    -0.82
     Starr
    -0.82
     confirming
    -0.79
     entirely
    -0.79
     beginning
    -0.77
     afric
    -0.75
    ạm
    -0.75
    POSITIVE LOGITS
    Achtung
    0.81
     swimmers
    0.80
    ลัง
    0.78
    Geschäfts
    0.78
    ]{
    0.77
    Cinderella
    0.76
    Aldo
    0.76
    reda
    0.76
    Mitglieder
    0.75
    Schöne
    0.75
    Activations Density 0.001%

    No Known Activations