© 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. 116582
    Prev
    Next
    INDEX
    Explanations

    stream media video redirection river course

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

    The neuron is triggered by occurrences of the word “stream” (in any case).

    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
     penso
    -1.20
     folosi
    -1.02
    増えて
    -0.93
    れました
    -0.93
    のかもしれません
    -0.92
     vogliono
    -0.90
    ophenol
    -0.90
     emailed
    -0.89
     crescente
    -0.88
     stumbled
    -0.88
    POSITIVE LOGITS
     Stream
    1.45
     stream
    1.33
    lined
    1.27
    stream
    1.23
    STREAM
    1.16
     STREAM
    1.13
    Stream
    1.06
     inputStream
    1.03
     реки
    1.02
     курса
    0.99
    Activations Density 0.017%

    No Known Activations