© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111518
    Prev
    Next
    INDEX
    Explanations

    exploring cities and places

    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
     Geistes
    -2.27
     using
    -2.23
     Unterrichts
    -2.22
     Weiterbildung
    -2.16
     that
    -2.14
     used
    -2.08
     my
    -1.90
     use
    -1.84
     test
    -1.84
     оружи
    -1.78
    POSITIVE LOGITS
     ویتامین
    2.33
    ﻻ
    2.31
    
    2.28
    
    2.25
    ﻷ
    2.25
     municípios
    2.09
    ׇ
    2.06
     النبات
    2.06
    
    2.03
     délicieux
    1.99
    Activations Density 1.258%

    No Known Activations