© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13085
    Prev
    Next
    INDEX
    Explanations

    wheelchair and accessibility

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

    The neuron strongly activates on mentions of “wheelchair” and other wheelchair-related contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     видел
    -1.93
     brancas
    -1.89
     condicionado
    -1.86
     представители
    -1.84
     pintados
    -1.79
    スム
    -1.75
     vieille
    -1.73
    鲥
    -1.72
     étoile
    -1.72
     «
    -1.70
    POSITIVE LOGITS
    with
    2.33
    是非常
    2.19
    ”？
    2.14
    ！”
    2.05
    ⬮
    2.03
    what
    2.00
    ancing
    1.87
    If
    1.80
    是很
    1.78
    ｉ
    1.77
    Activations Density 0.010%

    No Known Activations