© 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. 99688
    Prev
    Next
    INDEX
    Explanations

    presenting findings or descriptions

    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
     to
    -1.98
    姈
    -1.62
     individuellen
    -1.61
     Ansicht
    -1.58
    xelles
    -1.58
    屢
    -1.57
     offiziellen
    -1.57
     außerord
    -1.54
    嚶
    -1.51
     sicheren
    -1.50
    POSITIVE LOGITS
    мая
    1.58
     how
    1.55
     
    1.54
    "
    1.53
    '
    1.52
     herrs
    1.52
     some
    1.50
    \
    1.46
     "'
    1.45
     در
    1.39
    Activations Density 0.060%

    No Known Activations