© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116051
    Prev
    Next
    INDEX
    Explanations

    DB, DBT, DBBM, DDBSh

    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
     proviso
    -0.83
    whether
    -0.77
     간
    -0.77
     nonetheless
    -0.77
     nhàng
    -0.75
    GetSize
    -0.73
    ÁND
    -0.73
     [`
    -0.72
    一気に
    -0.72
    끝
    -0.72
    POSITIVE LOGITS
     db
    1.00
     DB
    0.95
     Sanjay
    0.81
     Доб
    0.81
    consuming
    0.80
    他的
    0.79
     dob
    0.74
     DEB
    0.74
    项目
    0.73
     debating
    0.73
    Activations Density 0.046%

    No Known Activations