© 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. 10-GEMMASCOPE-RES-131K
    7. 15852
    Prev
    Next
    INDEX
    Explanations

    myopia or forward thinking

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on terms related to nearsightedness (e.g., “myopia,” “myopic,” “short-sighted”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𖥧
    -1.99
    𐑂
    -1.99
     мужчи
    -1.93
    ꜆
    -1.91
    棪
    -1.88
     penilaian
    -1.84
    ⇰
    -1.84
     Surprisingly
    -1.81
     pemer
    -1.80
     furthering
    -1.77
    POSITIVE LOGITS
    '
    2.22
    乄
    2.17
    咵
    2.16
    
    2.05
    ly
    2.03
    𓍊
    2.00
    you
    2.00
    ౭
    1.97
    AutoresizingMask
    1.94
    该如何
    1.92
    Activations Density 0.004%

    No Known Activations