© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    glaucoma diagnosis

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

    words related to eye conditions, particularly "Sikh" and "glaucoma".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
    at
    -3.03
    in
    -3.00
     This
    -2.94
    To
    -2.92
     We
    -2.86
     --
    -2.84
    ated
    -2.75
    At
    -2.73
     To
    -2.66
    For
    -2.59
    POSITIVE LOGITS
    
    3.86
    蟶
    3.81
    鬻
    3.50
    🫅
    3.47
    ⎔
    3.39
    🫃
    3.38
    𓆏
    3.27
    
    3.17
    mpagne
    3.14
    憷
    3.14
    Activations Density 0.011%

    No Known Activations