© 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. 11710
    Prev
    Next
    INDEX
    Explanations

    some, each, any, both, many

    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
    这个
    -2.77
    >
    -2.75
    to
    -2.69
    -
    -2.66
    R
    -2.58
    -2.55
    W
    -2.50
    '
    -2.39
    :
    -2.36
    F
    -2.31
    POSITIVE LOGITS
     accordance
    2.70
    
    2.45
     发型
    2.22
     Then
    2.08
    櫺
    2.05
     persino
    2.02
     PUSTAKA
    1.98
    ⢮
    1.98
    .''
    1.96
    犛
    1.93
    Activations Density 0.095%

    No Known Activations