© 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. 39931
    Prev
    Next
    INDEX
    Explanations

    games, wins, records, appearances

    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
     did
    -1.46
     new
    -1.37
     didn
    -1.31
     one
    -1.19
     didnt
    -1.16
     should
    -1.15
     like
    -1.14
     Did
    -1.13
     then
    -1.12
     it
    -1.10
    POSITIVE LOGITS
     lifetime
    1.28
     différentes
    1.27
     years
    1.20
    various
    1.19
    amazing
    1.19
     verbe
    1.18
    whatever
    1.17
     никогда
    1.16
    Collected
    1.16
    Cumulative
    1.15
    Activations Density 0.035%

    No Known Activations