© 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. 95689
    Prev
    Next
    INDEX
    Explanations

    information seeking questions

    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
    たびに
    -1.33
     bayi
    -1.32
    gebraucht
    -1.29
     intrigu
    -1.28
     klasik
    -1.25
     unequiv
    -1.23
     organik
    -1.20
    取决
    -1.20
     exorbit
    -1.20
     arou
    -1.20
    POSITIVE LOGITS
     how
    2.86
     what
    2.44
     why
    2.05
     where
    1.88
     about
    1.84
     then
    1.84
     What
    1.83
     How
    1.73
     other
    1.59
     Why
    1.56
    Activations Density 0.009%

    No Known Activations