© 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. 12844
    Prev
    Next
    INDEX
    Explanations

    health risks and conditions

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

    diseases, injuries, and negative health outcomes

    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
    RestTemplate
    0.47
     εφαρ
    0.47
    广场
    0.46
     వీ
    0.46
    न्होंने
    0.46
     किफायती
    0.46
    🆕
    0.45
    🆓
    0.45
    🏁
    0.45
     المقسوم
    0.44
    POSITIVE LOGITS
     complications
    0.94
     cancers
    0.89
     atherosclerosis
    0.84
     diseases
    0.82
     enfermedades
    0.82
     neurological
    0.78
     morbidity
    0.78
     pancreatitis
    0.78
     osteoporosis
    0.77
     psychosis
    0.77
    Activations Density 0.098%

    No Known Activations