© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116002
    Prev
    Next
    INDEX
    Explanations

    once again

    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
    究竟
    -0.07
    だから
    -0.06
     trasport
    -0.06
    َد
    -0.06
    生まれた
    -0.06
     pubblicato
    -0.06
     abordagem
    -0.06
     minden
    -0.06
     erbjuder
    -0.06
     පමණ
    -0.06
    POSITIVE LOGITS
    なども
    0.06
     देखील
    0.06
     также
    0.05
     here
    0.05
    ಪ್
    0.05
     ஏற்படும்
    0.05
    Также
    0.05
    এক
    0.05
     ventricle
    0.05
     দেওয়া
    0.05
    Activations Density 0.002%

    No Known Activations