© 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. 83094
    Prev
    Next
    INDEX
    Explanations

    pages, price, age

    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
     example
    -0.86
    の人気
    -0.85
    tudiant
    -0.84
     popolari
    -0.82
     قاشق
    -0.81
     beachten
    -0.79
     Hoffmann
    -0.79
    篩
    -0.78
     INSTITUTION
    -0.78
     examples
    -0.77
    POSITIVE LOGITS
     Reviewed
    0.92
    Diesel
    0.91
    $$
    0.84
     reviewer
    0.83
    También
    0.83
     quidem
    0.82
    zension
    0.82
     REVIEW
    0.81
    bA
    0.81
    cC
    0.80
    Activations Density 0.056%

    No Known Activations