© 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. 186356
    Prev
    Next
    INDEX
    Explanations

    health, medicine, and technology

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

    handling requirements, catholic theology

    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
    ইন
    0.47
    קי
    0.46
    leftChild
    0.45
    न्यूयॉर्क
    0.45
     सुपरहिट
    0.45
    ﻁ
    0.45
    ጠቀም
    0.45
    ка
    0.45
    ත්තේ
    0.44
     क्यूट
    0.44
    POSITIVE LOGITS
    ;
    0.57
     Health
    0.54
     Ophthalmology
    0.52
     Birth
    0.51
     Pulse
    0.51
     Nutr
    0.51
     Kanban
    0.49
     Asthma
    0.49
     Crohn
    0.48
     здравоохранения
    0.48
    Activations Density 0.000%

    No Known Activations