© 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. 103505
    Prev
    Next
    INDEX
    Explanations

    powder

    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
    Trash
    -0.94
    leswig
    -0.85
    滴
    -0.80
     Trash
    -0.79
     évi
    -0.79
     BERNAMA
    -0.75
    dil
    -0.75
     litres
    -0.75
     šť
    -0.74
    ocities
    -0.73
    POSITIVE LOGITS
     powder
    4.06
     Powder
    3.16
    powder
    3.05
    Powder
    3.03
     powdered
    2.98
     powders
    2.81
     powdery
    2.42
    粉
    2.41
     dusting
    1.98
     poudre
    1.84
    Activations Density 0.059%

    No Known Activations