© 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. 115860
    Prev
    Next
    INDEX
    Explanations

    examples and datasets

    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
     ideal
    -0.06
     specific
    -0.06
     różnych
    -0.06
     வடிவமை
    -0.06
     different
    -0.06
    欣賞
    -0.06
    构
    -0.06
    composed
    -0.06
     respect
    -0.06
     टेस्टिंग
    -0.06
    POSITIVE LOGITS
     రిలీ
    0.06
     સમયે
    0.06
     tabuleiro
    0.06
    hofer
    0.06
    시는
    0.06
    启用
    0.06
     velha
    0.06
     hout
    0.06
     lingue
    0.06
     scant
    0.06
    Activations Density 0.007%

    No Known Activations