© 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. 119661
    Prev
    Next
    INDEX
    Explanations

    attribution by news sources

    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
     then
    -1.46
    řízen
    -1.33
     behulp
    -1.23
     prace
    -1.23
    providedIn
    -1.21
    chränkungen
    -1.21
     dormitorios
    -1.17
    ="{
    -1.17
     phun
    -1.16
     mostly
    -1.14
    POSITIVE LOGITS
    两个
    1.41
     étr
    1.38
     améli
    1.32
     relâche
    1.31
     ۱۴۰۰
    1.29
     expédi
    1.28
     nimmer
    1.28
    никам
    1.28
                   
    1.27
     sejak
    1.27
    Activations Density 0.179%

    No Known Activations