© 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. 22-GEMMASCOPE-RES-131K
    7. 16038
    Prev
    Next
    INDEX
    Explanations

    comparison studies

    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_22/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
    反应过来
    -1.15
     llegará
    -1.04
    起きた
    -1.03
     Compromise
    -1.03
     кари
    -1.02
    ญี่ป
    -1.02
    ครื่อง
    -1.02
     bucal
    -1.01
    iculture
    -0.99
     catedral
    -0.98
    POSITIVE LOGITS
     comparison
    2.94
     comparing
    2.50
     comparisons
    2.44
     Comparison
    2.16
     comparative
    2.05
     compare
    2.02
     срав
    1.95
    Comparing
    1.95
    Comparison
    1.89
    comparing
    1.83
    Activations Density 0.070%

    No Known Activations