© 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. 9499
    Prev
    Next
    INDEX
    Explanations

    introduces contrast

    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
     the
    -1.98
    趿
    -1.80
     estén
    -1.78
    ίος
    -1.73
     desean
    -1.72
    ureux
    -1.70
    </b>
    -1.70
    蟜
    -1.70
    に行きました
    -1.67
    纐
    -1.66
    POSITIVE LOGITS
    .
    2.78
     more
    1.95
    0
    1.86
      
    1.77
     Some
    1.72
     portanto
    1.71
    从来没有
    1.71
                    
    1.69
                        
    1.66
    Their
    1.66
    Activations Density 0.027%

    No Known Activations