© 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. 34-GEMMASCOPE-RES-131K
    4. 45399
    Prev
    Next
    INDEX
    Explanations

    media release and streaming

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

    The main thing this neuron does is spot words related to a show or film’s release schedule and distribution (e.g. “season,” “will,” “air,” “Netflix,” “streaming,” “debut”).

    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
    ientí
    -0.94
    icken
    -0.92
     during
    -0.85
     coral
    -0.84
    :
    -0.83
     sector
    -0.80
    מעות
    -0.79
     >
    -0.79
    Modificar
    -0.79
     stark
    -0.78
    POSITIVE LOGITS
     streaming
    1.84
    配信
    1.45
    streaming
    1.43
     streamer
    1.38
    Netflix
    1.37
     Netflix
    1.35
     Streaming
    1.34
    Available
    1.34
     stream
    1.30
     disponibile
    1.29
    Activations Density 0.014%

    No Known Activations