© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107469
    Prev
    Next
    INDEX
    Explanations

    auto parts or cars

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

    This neuron responds strongly to specific automobile model designations—especially year, make, model, and trim identifiers.

    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
     Factor
    -0.85
     bestehen
    -0.84
     Factors
    -0.75
     FACTOR
    -0.73
    otheses
    -0.73
    Factor
    -0.73
    Group
    -0.73
     Groups
    -0.70
     factor
    -0.69
     тари
    -0.69
    POSITIVE LOGITS
     importers
    1.11
     auction
    1.03
     importation
    1.02
     importing
    1.01
     imported
    1.01
    Auction
    0.98
     Imported
    0.98
    Imported
    0.96
    auction
    0.94
     Importing
    0.94
    Activations Density 0.021%

    No Known Activations