© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77934
    Prev
    Next
    INDEX
    Explanations

    add or create

    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_34/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
    setFilter
    -0.81
     巨
    -0.75
    انا
    -0.74
    onPage
    -0.73
    шёл
    -0.72
     coron
    -0.71
     Gutenberg
    -0.70
    selectBy
    -0.70
     "?
    -0.68
     $^{\
    -0.68
    POSITIVE LOGITS
     add
    1.57
     added
    1.55
     adding
    1.48
     добавить
    1.34
     добавля
    1.32
     addNew
    1.32
    Add
    1.26
    add
    1.26
    เพิ่ม
    1.23
     thêm
    1.23
    Activations Density 0.042%

    No Known Activations