© 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. 89881
    Prev
    Next
    INDEX
    Explanations

    linked list nodes

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

    The neuron flags programming‐language code elements—especially C/C++ keywords, function names, includes, and identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Prerequisite
    -0.73
    getJSONArray
    -0.72
    lapi
    -0.72
    ácie
    -0.70
    ユニクロ
    -0.67
    Lectures
    -0.67
    Pró
    -0.67
     Aérea
    -0.66
    商店街
    -0.65
     Strat
    -0.65
    POSITIVE LOGITS
     node
    2.66
    Node
    2.48
     Node
    2.45
     nodes
    2.30
    node
    2.25
    节点
    1.99
    NODE
    1.97
     Nodes
    1.92
    getNode
    1.86
    ListNode
    1.84
    Activations Density 0.029%

    No Known Activations