© 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. 70554
    Prev
    Next
    INDEX
    Explanations

    CORS and relative imports

    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
     When
    -2.59
     If
    -2.55
     Когда
    -2.41
     While
    -2.38
     Even
    -2.30
     Though
    -2.27
     Sometimes
    -2.25
    While
    -2.20
     Often
    -2.13
     Does
    -2.11
    POSITIVE LOGITS
    
    2.33
    </strong>
    2.33
    鹇
    2.33
    襌
    2.23
    
    2.23
    夘
    2.19
    ῞
    2.03
     transacción
    2.03
     gratuit
    2.03
    FormTagHelper
    2.02
    Activations Density 0.005%

    No Known Activations