© 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. 10-GEMMASCOPE-RES-131K
    7. 73599
    Prev
    Next
    INDEX
    Explanations

    left panel, Node

    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
    -2.38
    O
    -2.31
      
    -2.22
    {
    -2.08
    Historically
    -2.05
    Typically
    -2.02
    ”
    -1.95
     लेकिन
    -1.85
     帶
    -1.85
    ↵↵
    -1.84
    POSITIVE LOGITS
     swayed
    2.28
    蒟
    2.20
    
    2.17
    
    2.17
    "....
    2.16
    齶
    2.11
    铊
    2.09
    
    2.09
     Países
    2.05
     איך
    2.02
    Activations Density 0.031%

    No Known Activations