© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11575
    Prev
    Next
    INDEX
    Explanations

    linked list nodes

    np_acts-logits-general · gemini-2.5-flash-lite

    nodes in lists or graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glaze
    0.44
     worldview
    0.43
     subarrays
    0.42
     subarray
    0.41
     giới
    0.41
     برش
    0.40
     Shak
    0.40
    魉
    0.39
    ουν
    0.39
     প্রার্থীদের
    0.39
    POSITIVE LOGITS
     node
    1.71
    node
    1.66
     nodes
    1.65
    Node
    1.64
     Nodes
    1.64
     Node
    1.63
    节点
    1.61
    节点的
    1.53
    Nodes
    1.49
    nodes
    1.45
    Activations Density 0.067%

    No Known Activations