© 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. 123596
    Prev
    Next
    INDEX
    Explanations

    blog posts and social networking

    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
    
    -1.38
    饪
    -1.38
    
    -1.36
    isert
    -1.35
     används
    -1.35
    ayout
    -1.28
     incorpora
    -1.26
     conhecido
    -1.26
     PUEDE
    -1.24
     pioggia
    -1.23
    POSITIVE LOGITS
     with
    1.42
    _
    1.38
     of
    1.34
     any
    1.30
     without
    1.28
    </strong>
    1.27
     there
    1.16
    1
    1.16
     first
    1.13
    :
    1.11
    Activations Density 0.029%

    No Known Activations