© 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. 28098
    Prev
    Next
    INDEX
    Explanations

    few, small, tiny, one, two

    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
     of
    -1.17
     コスプレ
    -1.16
     forskellige
    -1.12
     why
    -1.05
     dalej
    -1.05
     DIFFERENT
    -0.98
    different
    -0.96
    WithMany
    -0.96
     quinn
    -0.95
     アンティーク
    -0.94
    POSITIVE LOGITS
     one
    1.72
     just
    1.48
     merely
    1.46
     only
    1.41
     small
    1.34
     barely
    1.30
     pequeño
    1.29
     few
    1.28
     tiny
    1.25
     two
    1.23
    Activations Density 0.059%

    No Known Activations