© 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. 129834
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
    -1.80
            
    -1.76
      
    -1.73
    p
    -1.71
    even
    -1.68
     даже
    -1.65
    se
    -1.58
                
    -1.55
    as
    -1.55
    a
    -1.53
    POSITIVE LOGITS
     pascua
    1.56
     vloer
    1.52
     triko
    1.51
     zijne
    1.50
     hunne
    1.49
     controladores
    1.48
     toalla
    1.45
     ammat
    1.45
     eene
    1.45
     playera
    1.43
    Activations Density 0.331%

    No Known Activations