© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17190
    Prev
    Next
    INDEX
    Explanations

    health and disease awareness

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

    mental illness and health support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    貿易
    0.55
     निर्यात
    0.45
     設計
    0.45
    業
    0.44
    設計
    0.44
    geqq
    0.43
     विश्लेषण
    0.43
    オブジェクト
    0.43
    結局
    0.42
    貨
    0.42
    POSITIVE LOGITS
     sufferers
    1.03
     sufferer
    0.97
     epilepsy
    0.89
     stigma
    0.87
     disease
    0.83
     Crohn
    0.82
     بیماری
    0.82
     hastalık
    0.82
     psoriasis
    0.80
     Epilepsy
    0.79
    Activations Density 0.142%

    No Known Activations