© 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. 82446
    Prev
    Next
    INDEX
    Explanations

    saddle and saddlebags

    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
    tres
    -0.76
    chata
    -0.76
     Edge
    -0.75
     pickle
    -0.74
    aleigh
    -0.73
     Families
    -0.73
    celtic
    -0.71
     edges
    -0.71
    casque
    -0.71
     Witten
    -0.70
    POSITIVE LOGITS
    bags
    1.34
    bag
    1.24
    Bags
    0.89
    bred
    0.85
     bags
    0.81
    BAG
    0.81
    Bag
    0.79
     IBOutlet
    0.76
    back
    0.75
     Sore
    0.74
    Activations Density 0.020%

    No Known Activations