© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39336
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     forbindelse
    -1.67
     dizendo
    -1.49
     hjælp
    -1.44
     illustratie
    -1.42
    aning
    -1.39
     henvis
    -1.38
     forbin
    -1.38
    vidade
    -1.38
     cheio
    -1.34
     detaljer
    -1.33
    POSITIVE LOGITS
     there
    1.80
    There
    1.57
     -
    1.55
           
    1.41
        
    1.41
     Allerdings
    1.35
              
    1.34
                   
    1.33
       
    1.31
             
    1.30
    Activations Density 0.345%

    No Known Activations