© 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. 42442
    Prev
    Next
    INDEX
    Explanations

    variables and identifiers

    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
    There
    -2.80
     Despite
    -2.70
     two
    -2.70
     There
    -2.64
    Two
    -2.48
     Since
    -2.45
     one
    -2.42
     this
    -2.39
     with
    -2.39
     first
    -2.34
    POSITIVE LOGITS
     semelh
    2.58
     insanely
    2.55
    
    2.39
     ridiculously
    2.36
    
    2.33
    
    2.31
     decidedly
    2.28
    赑
    2.28
    
    2.20
    
    2.20
    Activations Density 0.016%

    No Known Activations