© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128775
    Prev
    Next
    INDEX
    Explanations

    was primarily

    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
     \
    -2.00
    Like
    -1.84
     [
    -1.73
     meneg
    -1.70
     Firstly
    -1.69
    %")
    -1.68
    ourcen
    -1.63
     melakukannya
    -1.63
    meldet
    -1.62
    ２
    -1.62
    POSITIVE LOGITS
    '
    1.82
    "
    1.76
     between
    1.74
     either
    1.73
     a
    1.72
     entró
    1.71
     apareció
    1.62
    
    1.60
     something
    1.60
     dejó
    1.56
    Activations Density 0.099%

    No Known Activations