© 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. 66292
    Prev
    Next
    INDEX
    Explanations

    safety assessments

    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
    _
    -2.03
    </strong>
    -1.86
            
    -1.64
                                   
    -1.63
          
    -1.59
        
    -1.52
         
    -1.51
                    
    -1.50
     ofrecemos
    -1.48
              
    -1.47
    POSITIVE LOGITS
    but
    1.80
     这个
    1.63
     the
    1.56
     compleanno
    1.55
     verschied
    1.52
    according
    1.49
    ailleurs
    1.48
    こうした
    1.48
     theses
    1.45
     protracted
    1.45
    Activations Density 0.014%

    No Known Activations