© 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. 118660
    Prev
    Next
    INDEX
    Explanations

    followed by specific content

    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
    Negative Logits
     that
    -0.08
     que
    -0.06
     Get
    -0.06
     gets
    -0.06
     शुरुआती
    -0.06
     get
    -0.06
     vibrant
    -0.06
     первых
    -0.05
     decisive
    -0.05
    咱
    -0.05
    POSITIVE LOGITS
     Alps
    0.07
     każ
    0.06
     endeavoured
    0.06
     আবশ্যক
    0.06
    блоки
    0.06
    民宿
    0.06
     muß
    0.06
     vermek
    0.06
     yachts
    0.06
     debía
    0.06
    Activations Density 0.003%

    No Known Activations