© 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. 34-GEMMASCOPE-RES-131K
    7. 34891
    Prev
    Next
    INDEX
    Explanations

    doubly linked lists

    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
    лены
    -0.76
    𝕫
    -0.75
    шта
    -0.74
    reshed
    -0.72
    Precalculus
    -0.71
    jiri
    -0.70
    Goblin
    -0.69
     Mand
    -0.68
    ườ
    -0.68
     rapporti
    -0.67
    POSITIVE LOGITS
     linked
    4.25
     Linked
    3.55
    linked
    3.42
    Linked
    3.22
    LinkedList
    2.88
     LinkedList
    2.61
    链表
    2.50
    linkedList
    2.03
     LINK
    2.03
     singly
    2.02
    Activations Density 0.116%

    No Known Activations