© 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. 50360
    Prev
    Next
    INDEX
    Explanations

    vision and blindness

    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
     Hayek
    -0.72
     soporte
    -0.72
    imente
    -0.71
    会館
    -0.71
    𝒉
    -0.70
     сол
    -0.70
    ('--
    -0.69
     olhando
    -0.69
     PPP
    -0.68
     {'
    -0.68
    POSITIVE LOGITS
     sighted
    1.30
     blindness
    1.10
    sighted
    0.95
     blind
    0.95
     visually
    0.94
     sight
    0.93
     vision
    0.88
     ORIENT
    0.85
    視
    0.84
    Vision
    0.82
    Activations Density 0.016%

    No Known Activations