© 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. 34-GEMMASCOPE-RES-131K
    7. 70099
    Prev
    Next
    INDEX
    Explanations

    django abbreviations and structure

    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
    ieza
    -0.84
     struck
    -0.83
     feine
    -0.79
    nastics
    -0.77
    atalos
    -0.75
     виправи
    -0.74
     uppgifter
    -0.73
     tider
    -0.73
     schöne
    -0.73
     sabia
    -0.73
    POSITIVE LOGITS
    shortcuts
    0.97
     HttpResponse
    0.89
     shortcuts
    0.88
     __
    0.84
    缩
    0.82
    AMP
    0.78
    db
    0.77
    rewrite
    0.75
    บ
    0.75
    icht
    0.75
    Activations Density 0.008%

    No Known Activations