© 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. 84268
    Prev
    Next
    INDEX
    Explanations

    Red Bull BC One

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

    The neuron specifically detects mentions of the “Red Bull BC One” event name.

    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
     Stamm
    -0.69
    笔
    -0.68
    lessness
    -0.66
    ΤΟ
    -0.64
     viết
    -0.64
    hler
    -0.64
     mop
    -0.64
     cull
    -0.63
     unter
    -0.63
    bergs
    -0.62
    POSITIVE LOGITS
    Save
    0.69
    ╦
    0.66
    боре
    0.66
    altra
    0.66
    อิง
    0.65
    лений
    0.65
     ساب
    0.65
     Clarence
    0.64
    ))-
    0.64
     Tanto
    0.64
    Activations Density 0.071%

    No Known Activations