© 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. 34-GEMMASCOPE-RES-131K
    7. 118284
    Prev
    Next
    INDEX
    Explanations

    nothingness, absence, or negation

    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_34/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
     may
    -0.86
    可能
    -0.81
    bably
    -0.74
    lenül
    -0.74
    तीय
    -0.73
    CREAT
    -0.72
     может
    -0.70
     vielleicht
    -0.69
     pulgadas
    -0.68
     właśnie
    -0.68
    POSITIVE LOGITS
     neither
    1.89
     keinerlei
    1.73
     nothing
    1.50
    neither
    1.47
    Neither
    1.41
     هیچ
    1.41
     никаких
    1.31
    没有任何
    1.28
     offers
    1.27
    ไม่มี
    1.24
    Activations Density 0.101%

    No Known Activations