© 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. 128067
    Prev
    Next
    INDEX
    Explanations

    percentages or polls

    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
    这个问题
    -0.06
     অহ
    -0.06
    ることができる
    -0.06
    )
    -0.06
    았
    -0.06
     我
    -0.06
     version
    -0.06
     追加
    -0.06
     V
    -0.06
    version
    -0.06
    POSITIVE LOGITS
     algorit
    0.06
     Algorithms
    0.06
     nueve
    0.06
     builds
    0.06
     millions
    0.06
     wielu
    0.06
     снижение
    0.06
     diminu
    0.06
     linking
    0.06
     thrilling
    0.06
    Activations Density 0.010%

    No Known Activations