© 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. 12728
    Prev
    Next
    INDEX
    Explanations

    phrases starting with prepositions or introductory words

    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
     then
    -1.79
     would
    -1.72
    //};
    -1.31
    gigi
    -1.30
     a
    -1.27
     asamblea
    -1.27
    autoreleasepool
    -1.24
    ☆、
    -1.20
    ballon
    -1.20
     membuat
    -1.20
    POSITIVE LOGITS
    :
    1.36
     which
    1.35
     that
    1.33
    ISY
    1.13
     /
    1.07
     externos
    1.06
    hoff
    1.06
    DeclareMath
    1.05
     depositphotos
    1.05
     shutterstock
    1.05
    Activations Density 0.133%

    No Known Activations