© 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. 129114
    Prev
    Next
    INDEX
    Explanations

    percentage off a price

    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
    ’
    -2.03
     {
    -1.94
    \
    -1.92
     evangé
    -1.90
    

    -1.88
    salms
    -1.84
    们的
    -1.84
     
    -1.84
     vetorial
    -1.71
    随之
    -1.71
    POSITIVE LOGITS
     for
    2.33
     in
    2.23
    我们
    2.08
     These
    1.80
    We
    1.76
     or
    1.73
     untuk
    1.73
     bahagia
    1.72
     when
    1.72
    𝙀
    1.70
    Activations Density 0.004%

    No Known Activations