© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90660
    Prev
    Next
    INDEX
    Explanations

    creativecommons and licenses

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

    The neuron fires on references to open‐content licensing terms, especially Creative Commons and public‐domain statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    いよいよ
    -1.55
    春天
    -1.46
     sidan
    -1.37
    {
    -1.35
    пом
    -1.35
    』。
    -1.31
    呼ば
    -1.30
     lengte
    -1.29
    был
    -1.26
    著者
    -1.24
    POSITIVE LOGITS
     Fazit
    1.40
     недавно
    1.33
    creativecommons
    1.30
    Profesor
    1.23
     recently
    1.22
    ⡑
    1.18
     humility
    1.18
    recently
    1.17
    ulipas
    1.16
     biß
    1.16
    Activations Density 0.051%

    No Known Activations