© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67632
    Prev
    Next
    INDEX
    Explanations

    class definitions and properties

    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
    Those
    -1.16
    those
    -1.02
    これらの
    -0.97
     choisis
    -0.91
    Karakter
    -0.91
     desear
    -0.90
    itado
    -0.90
    Apar
    -0.90
    那些
    -0.88
     presion
    -0.88
    POSITIVE LOGITS
                                   
    0.81
    phosa
    0.79
    iNdEx
    0.79
     следующее
    0.77
     began
    0.77
     cuba
    0.77
     although
    0.77
     had
    0.77
    結び
    0.75
    ajoz
    0.75
    Activations Density 0.002%

    No Known Activations