© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10155
    Prev
    Next
    INDEX
    Explanations

    SQL INSERT SELECT

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

    The neuron fires most strongly on content‐heavy, topic-signaling words (e.g. section headings or other informative keywords that often open or highlight a new idea).

    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
    ен
    0.78
     Вам
    0.77
     мне
    0.72
    OrderId
    0.70
    ень
    0.69
    ক্ষণ
    0.69
     বলেছি
    0.68
     $^{
    0.68
    ям
    0.67
    дай
    0.67
    POSITIVE LOGITS
     gespielt
    0.91
     âge
    0.88
     primaire
    0.85
     éves
    0.83
    एक
    0.82
     légèrement
    0.80
     améliorer
    0.80
     créer
    0.80
     jouer
    0.80
    زا
    0.78
    Activations Density 0.000%

    No Known Activations