© 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. 73638
    Prev
    Next
    INDEX
    Explanations

    last names followed by punctuation or "and"

    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
     beſt
    -1.18
     himself
    -1.18
     sorprender
    -1.06
    himself
    -1.05
    gorithm
    -1.01
    siede
    -1.00
     fermer
    -1.00
    ///</
    -0.98
     preparo
    -0.97
     palet
    -0.96
    POSITIVE LOGITS
     without
    1.20
    謳
    1.07
    絆
    0.98
     until
    0.98
    姪
    0.97
     if
    0.95
     (
    0.92
    瞼
    0.91
    診療
    0.91
     Главная
    0.91
    Activations Density 0.002%

    No Known Activations