© 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. 83774
    Prev
    Next
    INDEX
    Explanations

    car repair and cleaning services

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

    The neuron primarily responds to common high-frequency function words (pronouns, articles, prepositions, and conjunctions).

    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
    Truck
    -0.79
    Melissa
    -0.78
    Linda
    -0.76
    Temp
    -0.75
    Travis
    -0.75
    Merchant
    -0.75
     farmacé
    -0.75
     pharmacy
    -0.74
    Mary
    -0.73
     stout
    -0.72
    POSITIVE LOGITS
     Teflon
    1.03
    workshop
    0.91
     undertake
    0.89
     Jha
    0.84
     undertaken
    0.84
     expert
    0.84
     undertook
    0.83
     AMC
    0.83
     workshop
    0.83
     experts
    0.83
    Activations Density 0.009%

    No Known Activations