© 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. 128225
    Prev
    Next
    INDEX
    Explanations

    followed by, then

    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
     IMG
    -0.07
    ╝
    -0.06
    也将
    -0.06
     ነገ
    -0.06
     also
    -0.06
     επίσης
    -0.06
    DQ
    -0.06
     myös
    -0.06
     수정
    -0.06
    also
    -0.06
    POSITIVE LOGITS
    ผ่าน
    0.06
     Riemannian
    0.06
     inspirado
    0.06
     liability
    0.06
     disparu
    0.06
     hearings
    0.06
     ผ่าน
    0.06
     omnis
    0.06
     novelist
    0.06
     koriste
    0.05
    Activations Density 0.008%

    No Known Activations