© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112075
    Prev
    Next
    INDEX
    Explanations

    wander, wandering, wanderers

    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
    
    -2.94
    軚
    -2.92
    饪
    -2.91
    
    -2.80
    
    -2.75
    
    -2.70
    髕
    -2.67
    
    -2.59
    zaSy
    -2.59
     autorisés
    -2.56
    POSITIVE LOGITS
     succinct
    3.13
     facets
    2.72
    of
    2.72
    -"
    2.66
    she
    2.55
     swoop
    2.52
    ."
    2.50
     Following
    2.48
     resolute
    2.48
     consummate
    2.42
    Activations Density 0.002%

    No Known Activations