© 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. 43805
    Prev
    Next
    INDEX
    Explanations

    article summaries and key messages

    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
    </strong>
    -1.94
     previous
    -1.50
      
    -1.49
    /*
    -1.44
     up
    -1.39
    cS
    -1.35
     aforementioned
    -1.33
     previamente
    -1.32
       
    -1.31
        
    -1.29
    POSITIVE LOGITS
     lage
    1.53
    葙
    1.44
    heden
    1.41
     ...
    1.41
     Jornal
    1.39
     Wörter
    1.38
     llor
    1.34
     Danmark
    1.33
     dedica
    1.32
    
    1.32
    Activations Density 0.062%

    No Known Activations