© 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. 22-GEMMASCOPE-RES-131K
    7. 10880
    Prev
    Next
    INDEX
    Explanations

    containing words and phrases

    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_22/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
     método
    -0.97
     dibuat
    -0.93
    bungs
    -0.85
    了出来
    -0.84
     or
    -0.84
     sienta
    -0.80
    እ
    -0.80
     podrá
    -0.79
     या
    -0.78
    }_{(
    -0.78
    POSITIVE LOGITS
     containing
    2.44
     contains
    1.89
     contenant
    1.88
    containing
    1.86
     Containing
    1.63
    包含
    1.62
     जिसमें
    1.61
    contains
    1.57
     حا
    1.57
     содержит
    1.55
    Activations Density 0.252%

    No Known Activations