© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118114
    Prev
    Next
    INDEX
    Explanations

    sight and vision

    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
    Lucifer
    -0.78
     bertujuan
    -0.77
     Gambar
    -0.73
    setNext
    -0.73
    ंबर
    -0.73
    Escrit
    -0.73
    Ami
    -0.72
    Diret
    -0.72
    Artigo
    -0.71
    onaceous
    -0.71
    POSITIVE LOGITS
     sight
    1.95
     vision
    1.87
     detection
    1.62
    sight
    1.52
     Vision
    1.45
     Sight
    1.44
    Vision
    1.42
     visibility
    1.41
    Sight
    1.41
     eyesight
    1.39
    Activations Density 0.015%

    No Known Activations