© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14634
    Prev
    Next
    INDEX
    Explanations

    list or lists in various languages

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

    The neuron strongly responds to instructional or advisory sentences—especially questions and how-to statements that introduce tips or guidance.

    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_24_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
    ternal
    0.89
     그걸
    0.82
     Broadcast
    0.81
     Implicit
    0.81
    มัน
    0.79
    
    0.78
     Implementation
    0.76
    INotification
    0.76
     එය
    0.75
     esso
    0.75
    POSITIVE LOGITS
    一覧
    1.27
    有哪些
    1.24
    Berikut
    1.21
     различных
    1.14
    各式
    1.13
    小编
    1.13
     살펴보
    1.10
    这篇文章
    1.10
     перечис
    1.10
     voici
    1.09
    Activations Density 6.206%

    No Known Activations