© 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. 65947
    Prev
    Next
    INDEX
    Explanations

    with disabilities or special needs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     patients
    -0.98
     wrong
    -0.86
     TOOLS
    -0.84
     beat
    -0.81
    zkiem
    -0.78
    aving
    -0.78
     הט
    -0.77
    Tech
    -0.76
    liev
    -0.74
     setDate
    -0.73
    POSITIVE LOGITS
     disabilities
    1.88
     disability
    1.39
     disabling
    1.01
     Anggota
    0.99
     Disabilities
    0.99
     cognitive
    0.89
    Disability
    0.88
     severe
    0.88
     impairments
    0.85
     khuyến
    0.84
    Activations Density 0.052%

    No Known Activations