© 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. 10-GEMMASCOPE-RES-131K
    7. 11664
    Prev
    Next
    INDEX
    Explanations

    is followed by its

    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_10/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
     económicas
    -1.63
    jährige
    -1.59
     financieras
    -1.56
     budete
    -1.50
    っております
    -1.50
     Paglinawan
    -1.48
     grossesse
    -1.46
    ₜ
    -1.45
     médicas
    -1.43
     necesarias
    -1.41
    POSITIVE LOGITS
    着一
    1.55
    を使
    1.54
     a
    1.49
     nowadays
    1.42
     not
    1.40
    ↵
    1.34
     «
    1.33
     has
    1.30
     from
    1.27
    もの
    1.27
    Activations Density 0.077%

    No Known Activations