© 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. 48345
    Prev
    Next
    INDEX
    Explanations

    used cars, inventory, dealers

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

    The neuron strongly activates on numeric tokens and digit sequences (i.e. numbers, prices, counts, etc.).

    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
     النبات
    -0.79
    setCustom
    -0.75
    alumno
    -0.75
    ผลิต
    -0.74
     rented
    -0.73
    ouser
    -0.73
     Sensitive
    -0.72
     böl
    -0.72
     proiz
    -0.72
    ⲣ
    -0.71
    POSITIVE LOGITS
     inventory
    1.60
    inventory
    1.32
     Inventory
    1.23
     cars
    1.20
     financing
    1.18
    Inventory
    1.14
     inspection
    1.07
     inspected
    1.07
     dealer
    1.07
     vehicles
    1.06
    Activations Density 0.030%

    No Known Activations