© 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. 25704
    Prev
    Next
    INDEX
    Explanations

    wheelchair access and users

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

    The neuron strongly activates on mentions of wheelchairs or related “wheels” mobility‐aid terms.

    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
     Telephone
    -0.76
     Insomnia
    -0.76
     아
    -0.74
    adka
    -0.69
     choked
    -0.65
    اتر
    -0.64
    nehmung
    -0.64
    garage
    -0.64
    Chemicals
    -0.64
     サッカー
    -0.64
    POSITIVE LOGITS
     wheelchair
    2.77
     wheelchairs
    2.13
     Wheelchair
    1.89
    wheel
    1.80
     wheel
    1.74
     WHEEL
    1.64
     wheels
    1.64
    Wheel
    1.63
     chair
    1.59
     wheeled
    1.55
    Activations Density 0.022%

    No Known Activations