© 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. 22-GEMMASCOPE-RES-131K
    7. 130901
    Prev
    Next
    INDEX
    Explanations

    alternative or former 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_22/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
    gewiesen
    -1.41
     douze
    -1.30
     certainement
    -1.28
     quaisquer
    -1.27
     réserver
    -1.26
     deliciously
    -1.23
    potentially
    -1.23
     salade
    -1.23
    slightly
    -1.23
    
    -1.23
    POSITIVE LOGITS
     or
    3.83
    某个
    1.76
    某
    1.74
     или
    1.58
     an
    1.55
     unusually
    1.48
     without
    1.48
     a
    1.45
     either
    1.41
    或
    1.38
    Activations Density 0.086%

    No Known Activations