© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117392
    Prev
    Next
    INDEX
    Explanations

    accessibility and navigation controls

    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
    ONLINE
    -0.79
     ONLINE
    -0.77
    flexible
    -0.73
    嘮
    -0.73
    COMMON
    -0.71
    <0xC9>
    -0.71
     furent
    -0.70
    Emerald
    -0.70
     prospec
    -0.69
     cowardice
    -0.69
    POSITIVE LOGITS
     blind
    1.84
     accessibility
    1.80
     Blind
    1.77
     blindness
    1.70
     Accessibility
    1.67
    blind
    1.63
    Blind
    1.59
     sighted
    1.54
    Accessibility
    1.52
     deaf
    1.50
    Activations Density 0.040%

    No Known Activations