© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128217
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declarations

    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
    ntl
    -0.06
     ülke
    -0.06
     Comparable
    -0.06
     vált
    -0.06
     என்றும்
    -0.06
    protocols
    -0.06
     zmieni
    -0.06
     revolution
    -0.06
     বিপ্ল
    -0.06
    はどう
    -0.06
    POSITIVE LOGITS
     diseñar
    0.06
     gym
    0.06
     hilfreich
    0.06
    पयोग
    0.06
     primeira
    0.06
     refresher
    0.06
    長さ
    0.05
     첫
    0.05
     প্রতিটি
    0.05
     tamanho
    0.05
    Activations Density 0.003%

    No Known Activations