© 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. 4210
    Prev
    Next
    INDEX
    Explanations

    coat, coating, or closet

    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
     высоты
    -0.95
     declarations
    -0.90
     Declarations
    -0.89
     části
    -0.88
    ätie
    -0.87
     Mø
    -0.85
    what
    -0.82
    梱
    -0.82
     pomodoro
    -0.82
    isy
    -0.81
    POSITIVE LOGITS
    coat
    1.24
     Coat
    1.20
    Coat
    1.02
    🧥
    1.01
     hanger
    0.93
    veien
    0.85
    colgante
    0.84
    ↵
    0.84
     Coats
    0.84
    是非常
    0.83
    Activations Density 0.019%

    No Known Activations