© 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. 5946
    Prev
    Next
    INDEX
    Explanations

    symptoms and diagnosis of conditions

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

    health symptoms and concerns

    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
     демокра
    0.59
    电商
    0.58
     бизнеса
    0.57
     Democracy
    0.56
     музе
    0.55
     экономики
    0.52
     రచన
    0.52
    🗽
    0.52
    定价
    0.52
     финанси
    0.52
    POSITIVE LOGITS
     symptoms
    1.09
     diagnosed
    1.02
    症状
    1.02
     diagnosis
    1.00
     síntomas
    0.98
     symptom
    0.97
     sintomas
    0.94
     simpt
    0.92
     diagnose
    0.92
     sintomi
    0.92
    Activations Density 0.162%

    No Known Activations