© 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. 10-GEMMASCOPE-RES-131K
    7. 100507
    Prev
    Next
    INDEX
    Explanations

    streaming content

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

    The neuron activates on instances of the word “stream” (or its inflected form “streaming”) in the text.

    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
     Behaup
    -1.89
     Herausforderung
    -1.84
     Wahrnehmung
    -1.76
     Fähigkeit
    -1.75
    ペーン
    -1.72
     totalité
    -1.70
     Aussage
    -1.69
     BRARY
    -1.63
     we
    -1.63
    }
    -1.63
    POSITIVE LOGITS
    臜
    2.28
    ;
    1.97
    鬭
    1.84
     welkom
    1.84
     grosse
    1.84
    viembre
    1.82
    过去的
    1.81
    澌
    1.80
     ſee
    1.73
     тысячи
    1.73
    Activations Density 0.024%

    No Known Activations