© 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. 42031
    Prev
    Next
    INDEX
    Explanations

    sentence continuation after comma

    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
    Ī
    -1.95
    旁边的
    -1.88
     πρ
    -1.84
    麃
    -1.83
     Zorg
    -1.80
     艺术
    -1.80
    旁边
    -1.74
     sucul
    -1.73
     relojes
    -1.73
     totalement
    -1.73
    POSITIVE LOGITS
     to
    2.83
     or
    2.39
     in
    2.36
     at
    2.08
     With
    1.97
     as
    1.87
     (
    1.87
     with
    1.80
     on
    1.78
    '][
    1.71
    Activations Density 0.021%

    No Known Activations