© 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. 21945
    Prev
    Next
    INDEX
    Explanations

    colors: turquoise, aqua, cyan, magenta

    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
    in
    -2.44
    ètre
    -2.02
    そういえば
    -1.90
     fechado
    -1.88
    蘩
    -1.84
     ouvido
    -1.82
    ਲ਼
    -1.81
    
    -1.80
    縯
    -1.80
    la
    -1.80
    POSITIVE LOGITS
    ."
    1.98
     \
    1.92
    ?"
    1.84
     '
    1.79
    One
    1.72
    
    1.68
    ILERS
    1.68
    过程中
    1.66
    Other
    1.63
     儿
    1.59
    Activations Density 0.011%

    No Known Activations