© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2283
    Prev
    Next
    INDEX
    Explanations

    reports or statements made

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

    The neuron fires on news‐style attribution phrases—e.g. “According to an eyewitness who spoke with Daily Post”—marking tokens used to cite sources or reports.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     дом
    -0.73
    век
    -0.72
    ffd
    -0.71
    标
    -0.69
     pierdas
    -0.69
     máximo
    -0.68
    Gele
    -0.68
    婉
    -0.68
     maceta
    -0.68
    bers
    -0.68
    POSITIVE LOGITS
     our
    1.34
     correspondent
    1.09
     нашем
    1.07
     нашего
    1.07
     correspondents
    1.06
     naszych
    1.03
    可靠
    0.98
    信頼
    0.98
    Correspond
    0.96
     nosso
    0.95
    Activations Density 0.006%

    No Known Activations