© 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. 94720
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and treatments

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

    technical and problematic concepts

    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
     👇
    0.55
     सेटअप
    0.48
    لی
    0.47
    様専用
    0.47
     implementação
    0.46
     implementación
    0.46
     ⭐
    0.46
     ایف
    0.46
     ₽
    0.46
     बेहतरीन
    0.45
    POSITIVE LOGITS
     quinine
    0.53
     milder
    0.48
     aggravated
    0.47
     calomel
    0.46
    ]=
    0.45
     insensible
    0.45
     thirds
    0.45
     rheumatoid
    0.44
     lessened
    0.44
     aggravation
    0.44
    Activations Density 0.002%

    No Known Activations