© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
    from
    -1.62
     triliun
    -1.58
    dungen
    -1.55
    9
    -1.52
     to
    -1.49
    name
    -1.46
     morto
    -1.41
            
    -1.41
           
    -1.38
    TO
    -1.38
    POSITIVE LOGITS
     Почему
    1.70
     your
    1.57
     recomendar
    1.52
    ，“
    1.48
    efforts
    1.47
     можуть
    1.45
     mascarilla
    1.43
     ยัง
    1.41
     maravill
    1.41
     Frequently
    1.41
    Activations Density 0.018%

    No Known Activations