© 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. 92456
    Prev
    Next
    INDEX
    Explanations

    decoy maker

    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
     Yoon
    -0.79
    🫓
    -0.79
    щества
    -0.78
     goats
    -0.78
    chio
    -0.76
     pandas
    -0.75
    illante
    -0.75
     Papel
    -0.75
     abor
    -0.75
     animales
    -0.73
    POSITIVE LOGITS
     duck
    1.91
     Ducks
    1.60
    duck
    1.59
     waterfowl
    1.57
     Duck
    1.55
    Duck
    1.54
     ducks
    1.53
     drake
    1.41
    fowl
    1.22
    Ducks
    1.21
    Activations Density 0.016%

    No Known Activations