© 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. 127955
    Prev
    Next
    INDEX
    Explanations

    at least [number]

    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
     إذا
    -0.08
     if
    -0.08
     Jeśli
    -0.07
     gorillas
    -0.07
     algum
    -0.07
     algún
    -0.06
     Když
    -0.06
    dyž
    -0.06
     móviles
    -0.06
     Eğer
    -0.06
    POSITIVE LOGITS
     which
    0.06
     Rij
    0.06
     October
    0.05
    ):
    0.05
    using
    0.05
     промо
    0.05
    وطه
    0.05
    образова
    0.05
     using
    0.05
     inside
    0.05
    Activations Density 0.007%

    No Known Activations