© 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. 11678
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     rodas
    -2.06
    艄
    -2.05
    
    -1.91
    
    -1.91
     alho
    -1.83
     própri
    -1.83
     potenci
    -1.82
    雱
    -1.82
     indiví
    -1.80
     chers
    -1.80
    POSITIVE LOGITS
     not
    2.27
    ↵↵
    2.19
     in
    2.05
    6
    2.03
    3
    2.03
    9
    2.03
    7
    1.88
    4
    1.87
    5
    1.83
     and
    1.80
    Activations Density 0.019%

    No Known Activations