© 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. 104024
    Prev
    Next
    INDEX
    Explanations

    simple statements with punctuation

    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
     gesamten
    -1.57
     on
    -1.55
     nära
    -1.48
     damaligen
    -1.46
     ursprünglichen
    -1.42
    pág
    -1.38
     गर्न
    -1.38
     aktuellen
    -1.35
     gemens
    -1.32
     långt
    -1.28
    POSITIVE LOGITS
     you
    1.77
     после
    1.76
     ainda
    1.48
     its
    1.39
     vẫn
    1.38
     tetap
    1.29
    το
    1.27
    ulée
    1.26
    stanze
    1.24
     lors
    1.23
    Activations Density 0.096%

    No Known Activations