© 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. 34-GEMMASCOPE-RES-131K
    7. 106770
    Prev
    Next
    INDEX
    Explanations

    coffee, milk, or recipes

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

    The main thing this neuron does is detect coffee‐related beverage names or terms.

    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
     wine
    -0.90
     beer
    -0.89
     drape
    -0.88
     przypadku
    -0.86
     BEER
    -0.85
     черво
    -0.82
    咧
    -0.79
     BREAD
    -0.79
    beer
    -0.75
    equilibrium
    -0.75
    POSITIVE LOGITS
     latte
    1.52
     milk
    1.30
    Lat
    1.27
     Lat
    1.23
     Latte
    1.13
     Milk
    1.10
    latte
    1.09
     молока
    1.09
     lat
    1.08
    milk
    1.04
    Activations Density 0.013%

    No Known Activations