© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15735
    Prev
    Next
    INDEX
    Explanations

    linked lists and nodes

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

    The neuron strongly activates on numeric expressions and quantified constraints (numbers, measurements, or counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     pegatina
    0.57
    シール
    0.55
     arugula
    0.54
    敤
    0.53
    krieg
    0.52
    ☮
    0.52
    櫻
    0.52
    焗
    0.52
    ಾಗಲೇ
    0.52
    対応
    0.51
    POSITIVE LOGITS
     ListNode
    1.49
    ListNode
    1.48
     Node
    1.47
     node
    1.43
    Node
    1.38
     currentNode
    1.36
    node
    1.34
     Nodes
    1.33
     nodes
    1.30
     NODE
    1.27
    Activations Density 0.021%

    No Known Activations