© 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. 70249
    Prev
    Next
    INDEX
    Explanations

    whether to allow

    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
    ed
    -1.95
     niedersachsen
    -1.84
    饜
    -1.79
     westfalen
    -1.61
    dding
    -1.60
     doivent
    -1.59
     Rè
    -1.55
    
    -1.54
     全新
    -1.52
     gastronomía
    -1.48
    POSITIVE LOGITS
             
    1.55
     while
    1.52
           
    1.51
               
    1.48
     on
    1.48
     as
    1.47
        
    1.46
          
    1.42
     some
    1.41
                
    1.38
    Activations Density 0.014%

    No Known Activations