© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, symbols, and punctuation

    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
     reizen
    -1.13
    ราคา
    -1.05
    cile
    -1.01
    graphique
    -0.99
    :].
    -0.99
     ongel
    -0.96
    ciled
    -0.96
     then
    -0.96
    DotNetBar
    -0.95
    lineno
    -0.94
    POSITIVE LOGITS
     erweiter
    0.88
     sicherlich
    0.87
     zweifel
    0.85
     EVERY
    0.84
    Merged
    0.83
     humiliated
    0.79
     erweiterten
    0.78
    不能为空
    0.77
    普通的
    0.76
     vuestros
    0.76
    Activations Density 0.013%

    No Known Activations