© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    programs and sequences

    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
     gitara
    -0.88
     раскра
    -0.85
     klien
    -0.83
    zaron
    -0.79
     zanim
    -0.78
     Filtering
    -0.77
    useNewUrlParser
    -0.76
    Sergey
    -0.76
    퐼
    -0.75
     Ayuntamiento
    -0.75
    POSITIVE LOGITS
     programs
    1.11
     program
    1.08
     start
    1.06
    programs
    1.04
     Programs
    1.02
     delayed
    1.00
    Program
    0.99
     functions
    0.94
     Program
    0.92
    Soil
    0.92
    Activations Density 0.009%

    No Known Activations