© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129556
    Prev
    Next
    INDEX
    Explanations

    medical uses for health conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -0.06
     obsessed
    -0.06
     ನೀರಿನ
    -0.06
     menerapkan
    -0.05
     Sexy
    -0.05
     warned
    -0.05
     sampai
    -0.05
    CreateTable
    -0.05
     lưu
    -0.05
     எதிர்பார்க்க
    -0.05
    POSITIVE LOGITS
    缓解
    0.09
    乘坐
    0.07
     தினமும்
    0.07
    τούν
    0.07
    redu
    0.07
     повседнев
    0.07
     anest
    0.06
    常用
    0.06
     amelior
    0.06
     uses
    0.06
    Activations Density 0.012%

    No Known Activations