© 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. 115833
    Prev
    Next
    INDEX
    Explanations

    S,quoi,companies,as,Set

    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
     queremos
    -0.08
     вкус
    -0.07
    よりも
    -0.07
     bessere
    -0.07
     peningkatan
    -0.07
    मुळे
    -0.07
    보다
    -0.07
     сама
    -0.07
     quieren
    -0.06
     gebruikt
    -0.06
    POSITIVE LOGITS
     、
    0.06
     Sonia
    0.06
     ※
    0.06
     श्रीम
    0.05
    ,[
    0.05
     сооб
    0.05
     therm
    0.05
    ※
    0.05
    🌡
    0.05
     stars
    0.05
    Activations Density 0.003%

    No Known Activations