© 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. 70179
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    opardi
    -1.08
     INCLUDING
    -1.05
     翼
    -0.98
     Including
    -0.91
    定的
    -0.88
    Jîn
    -0.87
    IGNORE
    -0.84
    AfterEach
    -0.83
    =""><
    -0.82
    XmlRootElement
    -0.82
    POSITIVE LOGITS
     order
    6.50
     כדי
    4.16
     чтобы
    4.03
     để
    3.83
    เพื่อ
    3.72
    order
    3.64
    为了
    3.34
     inorder
    3.16
    Order
    3.16
     Order
    3.06
    Activations Density 0.215%

    No Known Activations