© 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. 47522
    Prev
    Next
    INDEX
    Explanations

    horse races and medical conditions

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

    information about horse racing and thoroughbreds, particularly race details, stakes, and horse classifications.

    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_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
     инте
    -0.80
    オリーブ
    -0.77
    hires
    -0.77
    lices
    -0.77
    늙
    -0.75
    ented
    -0.72
    jects
    -0.72
    μέν
    -0.72
    ția
    -0.71
     Ammonium
    -0.71
    POSITIVE LOGITS
     allowance
    0.99
     blue
    0.77
    Allowance
    0.75
    enapa
    0.72
     Blue
    0.72
     wooden
    0.69
     diving
    0.69
    λον
    0.69
    cbc
    0.69
     Alabama
    0.68
    Activations Density 0.065%

    No Known Activations