© 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. 124752
    Prev
    Next
    INDEX
    Explanations

    digits, numbers, years

    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
     wußte
    -1.79
    </u>
    -1.77
     when
    -1.63
     mengucap
    -1.60
     some
    -1.51
     which
    -1.49
     glaubte
    -1.45
    :[],
    -1.45
     鐵
    -1.39
     where
    -1.38
    POSITIVE LOGITS
     is
    1.78
    Your
    1.63
     would
    1.59
     \
    1.42
     will
    1.41
    SaveChangesAsync
    1.38
     souligne
    1.37
     are
    1.34
    である
    1.25
       
    1.23
    Activations Density 0.079%

    No Known Activations