© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38244
    Prev
    Next
    INDEX
    Explanations

    rules and standards books

    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
    0
    -0.98
    很简单
    -0.95
    6
    -0.94
    也不用
    -0.90
     composés
    -0.86
     هنوز
    -0.85
     erstre
    -0.84
    很有
    -0.84
    我不是
    -0.84
     infestations
    -0.84
    POSITIVE LOGITS
     book
    1.27
    book
    1.08
    atürk
    1.07
     tubos
    1.07
     Vainqueur
    1.05
     booklet
    1.04
     chapter
    1.03
    Book
    1.01
     Secretaria
    1.00
     Portuguesa
    1.00
    Activations Density 0.085%

    No Known Activations