© 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. 47662
    Prev
    Next
    INDEX
    Explanations

    upcoming week

    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
     两
    -1.55
    鲣
    -1.49
     喝
    -1.48
     意思
    -1.45
     From
    -1.44
     遇
    -1.44
     starken
    -1.43
     verá
    -1.40
     veran
    -1.39
     encontrará
    -1.36
    POSITIVE LOGITS
    and
    1.57
    then
    1.44
    。
    1.41
     Coated
    1.40
     Screws
    1.37
    ."
    1.36
    inä
    1.34
    焄
    1.34
    Acu
    1.34
    ain
    1.34
    Activations Density 0.050%

    No Known Activations