© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11402
    Prev
    Next
    INDEX
    Explanations

    medical conditions and symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    刑事
    0.43
     POLITICAL
    0.43
    纯
    0.42
     রাজনৈতিক
    0.41
    我们在
    0.41
    ajemy
    0.40
     полити
    0.39
    诛
    0.39
     মানবিক
    0.38
     социальных
    0.38
    POSITIVE LOGITS
     disease
    0.65
     symptoms
    0.59
     illness
    0.59
     заболе
    0.59
     malattia
    0.55
    disease
    0.54
    症状
    0.54
     affliction
    0.54
     sintomi
    0.52
     disorder
    0.51
    Activations Density 0.037%

    No Known Activations