© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56906
    Prev
    Next
    INDEX
    Explanations

    disabled, disability, Deaf

    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
    Negative Logits
     specjal
    -0.77
     Schlu
    -0.77
     monog
    -0.75
    iální
    -0.75
     Leal
    -0.74
     Tade
    -0.74
    >-</
    -0.73
    iál
    -0.73
    憨
    -0.71
    execu
    -0.69
    POSITIVE LOGITS
     disability
    1.25
     Disability
    1.21
    Disabled
    1.16
    disabled
    1.10
     Disabled
    1.09
    Disability
    1.05
     disabled
    1.02
     Deaf
    0.91
     oops
    0.86
     allies
    0.85
    Activations Density 0.030%

    No Known Activations