© 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. 6999
    Prev
    Next
    INDEX
    Explanations

    end of sentences or clauses

    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
    譏
    -1.02
     Había
    -1.00
    现在的
    -0.94
     izman
    -0.94
     such
    -0.93
     Vorschlag
    -0.91
    iramente
    -0.91
     THESE
    -0.88
     one
    -0.88
     cilvē
    -0.88
    POSITIVE LOGITS
     production
    1.96
    production
    1.71
     Production
    1.51
    Production
    1.41
     will
    1.41
     producción
    1.31
    expected
    1.27
    кож
    1.25
     expect
    1.22
     produced
    1.21
    Activations Density 0.064%

    No Known Activations