© 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. 34862
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers for events

    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
     first
    -1.49
     second
    -1.39
     third
    -1.08
     fourth
    -1.05
     fifth
    -1.05
     sixth
    -1.04
     seventh
    -1.02
     eighth
    -1.00
     ninth
    -0.97
     první
    -0.95
    POSITIVE LOGITS
     annual
    1.27
     biennial
    1.16
     Annual
    1.02
     graders
    1.00
     Asia
    1.00
     International
    0.97
     ilyen
    0.95
     еже
    0.94
    Annual
    0.91
     international
    0.90
    Activations Density 0.027%

    No Known Activations