© 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. 10-GEMMASCOPE-RES-131K
    7. 12018
    Prev
    Next
    INDEX
    Explanations

    brings about outcomes

    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_10/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
     of
    -1.85
     by
    -1.78
    撼
    -1.62
     has
    -1.59
    ством
    -1.58
     是
    -1.57
    .'”
    -1.57
     it
    -1.55
     kroner
    -1.55
    мся
    -1.42
    POSITIVE LOGITS
     Brings
    1.64
     spoluprá
    1.52
     instalment
    1.50
     работе
    1.48
     pojawi
    1.48
    簠
    1.48
    wachen
    1.46
    archiwizowane
    1.46
    Raises
    1.46
    فيلم
    1.43
    Activations Density 0.013%

    No Known Activations