© 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. 22-GEMMASCOPE-RES-131K
    7. 15313
    Prev
    Next
    INDEX
    Explanations

    family history of disease

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

    phrases related to family history or individuals with specific conditions or traits.

    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_22/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
     maneiras
    -1.01
     cuantos
    -0.98
     范
    -0.97
     destiné
    -0.94
    啶
    -0.93
     навіть
    -0.93
    rierte
    -0.92
     cidades
    -0.92
    {*}
    -0.91
    TAIN
    -0.91
    POSITIVE LOGITS
     or
    1.75
     ebenfalls
    1.30
     their
    1.27
     then
    1.16
    他們
    1.03
     similar
    1.01
     thier
    0.99
     themselves
    0.98
    μένος
    0.97
     provides
    0.96
    Activations Density 0.043%

    No Known Activations