© 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. 73388
    Prev
    Next
    INDEX
    Explanations

    barbecue

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

    The main thing this neuron does is detect mentions of “BBQ” or “barbecue.”

    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
    9
    -2.94
    7
    -2.61
    5
    -2.61
    4
    -2.58
    2
    -2.56
     :/
    -2.56
     gemeinsame
    -2.44
    
    -2.44
    8
    -2.39
     \
    -2.38
    POSITIVE LOGITS
    龊
    2.36
     explicado
    2.27
     decorados
    2.22
    zelfde
    2.19
    u
    2.16
     verschil
    2.09
    e
    2.09
    だそうです
    2.09
     semelhantes
    2.08
     sociais
    2.02
    Activations Density 0.003%

    No Known Activations