© 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. 65300
    Prev
    Next
    INDEX
    Explanations

    cumulative sum/total/average/effect/doses

    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
     his
    -1.30
    暮らし
    -1.20
    .].
    -1.18
     koniec
    -1.15
    
    -1.14
    dox
    -1.13
     irmã
    -1.13
     OBITUARY
    -1.13
     xay
    -1.13
     suy
    -1.12
    POSITIVE LOGITS
    нения
    1.35
    المصدر
    1.30
     accum
    1.14
    fjspx
    1.13
    بسم
    1.13
    المشار
    1.12
    تحميل
    1.11
    Bagi
    1.10
     spark
    1.09
     yapımı
    1.09
    Activations Density 0.049%

    No Known Activations