© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    Marvel VS, Often touted, “Author, what we

    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
     solcher
    -1.08
    եկ
    -1.03
     familiari
    -0.96
     orec
    -0.93
    mathrm
    -0.92
     sekaligus
    -0.91
     Hd
    -0.88
     opérations
    -0.88
    この
    -0.87
     niyang
    -0.86
    POSITIVE LOGITS
     other
    1.28
    ături
    1.05
     in
    1.05
    อื่น
    1.03
     between
    1.02
     from
    0.96
     zwischen
    0.93
    жели
    0.93
     двор
    0.92
     for
    0.91
    Activations Density 0.010%

    No Known Activations