© 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. 115651
    Prev
    Next
    INDEX
    Explanations

    dos and don'ts

    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
     Behör
    -0.78
    ਕ
    -0.77
    atization
    -0.75
    åter
    -0.74
    ս
    -0.73
     Noor
    -0.73
     ช
    -0.73
    ΰ
    -0.73
    Size
    -0.73
     Beverage
    -0.72
    POSITIVE LOGITS
     try
    2.59
    try
    2.39
     Try
    2.03
    Try
    1.95
     попробу
    1.76
     tries
    1.73
     TRY
    1.70
    TRY
    1.55
     attempt
    1.50
     tried
    1.45
    Activations Density 0.005%

    No Known Activations