© 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. 34-GEMMASCOPE-RES-131K
    7. 59539
    Prev
    Next
    INDEX
    Explanations

    February, comments, imports

    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_34/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
     поддержка
    -0.95
     semblables
    -0.87
     čia
    -0.83
    
    -0.83
     vgl
    -0.83
     heet
    -0.82
     répand
    -0.82
     procha
    -0.80
     koel
    -0.80
    的问道
    -0.79
    POSITIVE LOGITS
     shortly
    0.93
    مام
    0.87
     before
    0.86
     золота
    0.84
     all
    0.82
    金曜
    0.80
     Legion
    0.79
     path
    0.78
     only
    0.76
     strongly
    0.75
    Activations Density 0.003%

    No Known Activations