© 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. 70496
    Prev
    Next
    INDEX
    Explanations

    subject followed by has/have

    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
     their
    -1.59
     even
    -1.23
     when
    -1.16
     könnten
    -1.05
     atento
    -1.04
    最后
    -1.03
    pfen
    -1.02
     nantinya
    -1.02
     February
    -0.99
     их
    -0.99
    POSITIVE LOGITS
     has
    1.88
     have
    1.51
     olmuş
    1.41
     since
    1.30
     telah
    1.28
     đã
    1.25
     ongeveer
    1.13
    since
    1.12
     منذ
    1.12
     chaque
    1.10
    Activations Density 0.047%

    No Known Activations