© 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. 23464
    Prev
    Next
    INDEX
    Explanations

    café and coffee related terms

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

    The neuron fires on any token containing the “cafe/​caffe” string (i.e. coffee-related words and variations, including accented forms and derivatives).

    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
    INESS
    -0.88
     effetti
    -0.87
    也不敢
    -0.84
    ⓶
    -0.80
     eixo
    -0.80
    liess
    -0.80
    vikle
    -0.80
     revered
    -0.80
    を加
    -0.79
    ಾಗಿ
    -0.79
    POSITIVE LOGITS
    ☕️
    1.24
     Racer
    1.10
     racer
    1.09
    ́
    1.05
    ☕
    1.02
     Starbucks
    0.97
     latte
    0.97
     Caf
    0.96
    Racer
    0.95
    Caf
    0.95
    Activations Density 0.010%

    No Known Activations