© 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. 102923
    Prev
    Next
    INDEX
    Explanations

    possessions in pockets or bags

    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
     backpacks
    -1.22
     suitcases
    -1.20
     suitcase
    -1.05
    Pinterest
    -0.94
     baskets
    -0.91
     luggage
    -0.89
     buckets
    -0.88
     Luggage
    -0.85
     backpack
    -0.84
     tafel
    -0.84
    POSITIVE LOGITS
     wallet
    1.80
     keys
    1.74
     wallets
    1.47
    keys
    1.30
     tissues
    1.30
     cellphone
    1.27
     Wallet
    1.27
    Wallet
    1.25
    wallet
    1.21
     pens
    1.19
    Activations Density 0.026%

    No Known Activations