© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64977
    Prev
    Next
    INDEX
    Explanations

    conservation and restoration

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

    The neuron activates on language about conserving, protecting, or preserving cultural and historical heritage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     оружи
    -1.59
     you
    -1.54
    饷
    -1.53
    Menurutnya
    -1.47
    倖
    -1.45
    作战
    -1.45
    dây
    -1.40
    聯絡
    -1.39
     your
    -1.38
     United
    -1.36
    POSITIVE LOGITS
    ÈNE
    1.58
    ׇ
    1.49
    adır
    1.48
     scuole
    1.48
     Metode
    1.46
     Giochi
    1.46
    گوشی
    1.45
     specchio
    1.45
     Khart
    1.41
    atasi
    1.39
    Activations Density 0.065%

    No Known Activations