© 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. 83628
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and terms

    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
     diminish
    -1.54
     multifaceted
    -1.53
     supremely
    -1.41
     because
    -1.40
     severely
    -1.39
     spurred
    -1.38
    because
    -1.38
     completely
    -1.37
     meticulous
    -1.36
     blatantly
    -1.34
    POSITIVE LOGITS
     alcune
    1.58
     alcuni
    1.55
     alguns
    1.55
     algumas
    1.50
     SPECIAL
    1.35
     LOCAL
    1.29
     erhi
    1.28
     praktische
    1.27
     wacky
    1.25
     broader
    1.23
    Activations Density 0.004%

    No Known Activations