© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99022
    Prev
    Next
    INDEX
    Explanations

    coffee roasting and brewing processes

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

    This neuron detects detailed specialty‐coffee terminology—especially words describing the brewing process and sensory attributes (e.g. roasting, beans, aroma, flavor, body, temperature).

    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
     Armani
    -0.83
    disha
    -0.72
    ULAN
    -0.71
    DrawLine
    -0.71
    ާ
    -0.69
     radiador
    -0.68
    romycin
    -0.68
     глю
    -0.68
    mium
    -0.67
     rustling
    -0.67
    POSITIVE LOGITS
     City
    1.05
     underdeveloped
    1.03
    City
    0.92
     profiles
    0.90
    city
    0.90
     darkest
    0.88
     roast
    0.84
     darker
    0.83
     CITY
    0.82
     city
    0.81
    Activations Density 0.009%

    No Known Activations