© 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. 11514
    Prev
    Next
    INDEX
    Explanations

    years and centuries

    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
     neuen
    -1.51
    ຣ
    -1.48
     jejich
    -1.45
     wybór
    -1.38
    ственности
    -1.34
     اپنے
    -1.34
     двигателя
    -1.34
    或者是
    -1.33
    ῖς
    -1.32
     glaubt
    -1.32
    POSITIVE LOGITS
     of
    2.66
     it
    2.14
     to
    1.66
     النبات
    1.46
    ὕ
    1.41
    ﻻ
    1.30
    ἴ
    1.27
     famílias
    1.27
     before
    1.25
     muebles
    1.23
    Activations Density 0.549%

    No Known Activations