© 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. 48408
    Prev
    Next
    INDEX
    Explanations

    build process

    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
    rometry
    -0.84
    romycin
    -0.79
    CTOR
    -0.78
    😽
    -0.77
     edificio
    -0.77
     gitt
    -0.76
     construite
    -0.76
     Charley
    -0.74
     pregnancy
    -0.74
     bâtiment
    -0.73
    POSITIVE LOGITS
     script
    0.98
    script
    0.93
    system
    0.91
     system
    0.91
     process
    0.85
    targets
    0.78
     targets
    0.75
    ska
    0.74
    systems
    0.73
     systemu
    0.73
    Activations Density 0.065%

    No Known Activations