© 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. 115919
    Prev
    Next
    INDEX
    Explanations

    margin and padding units

    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
    Whats
    -0.06
     mentre
    -0.06
    whats
    -0.06
    Which
    -0.06
    Would
    -0.06
     mientras
    -0.06
    部屋
    -0.05
     What
    -0.05
     जबकि
    -0.05
     galore
    -0.05
    POSITIVE LOGITS
    自家
    0.07
     அளவு
    0.06
     établie
    0.06
     tow
    0.06
    遵循
    0.06
     uncertain
    0.06
     atyp
    0.06
    同様
    0.06
     aforementioned
    0.06
     allerlei
    0.06
    Activations Density 0.002%

    No Known Activations