© 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. 123766
    Prev
    Next
    INDEX
    Explanations

    Come followed by invitation

    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
     \
    -3.14
     is
    -2.58
     $
    -2.55
     '
    -2.50
    と
    -2.45
    A
    -2.41
     و
    -2.36
    N
    -2.36
    笑笑
    -2.34
     e
    -2.28
    POSITIVE LOGITS
    硨
    2.95
     vixion
    2.41
     itſelf
    2.34
    鷽
    2.33
    饜
    2.31
    ,
    2.27
     蜜
    2.25
     стоковые
    2.23
     麵
    2.19
    
    2.19
    Activations Density 0.010%

    No Known Activations