© 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. 22-GEMMASCOPE-RES-131K
    7. 39010
    Prev
    Next
    INDEX
    Explanations

    cannot remove undefined

    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_22/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
     stöd
    -1.06
     verste
    -0.84
     support
    -0.84
                            
    -0.79
     Team
    -0.77
                           
    -0.77
                        
    -0.74
    Translated
    -0.74
                    
    -0.73
                                  
    -0.73
    POSITIVE LOGITS
    ALREADY
    1.24
     already
    1.12
    already
    1.08
    Already
    1.08
     bereits
    1.08
    ContextCompat
    1.02
     zaten
    0.98
    タリー
    0.97
     כבר
    0.96
     이미
    0.94
    Activations Density 0.004%

    No Known Activations