© 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. 120862
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     события
    -0.07
    RENGTH
    -0.07
     és
    -0.07
     sowas
    -0.06
    StartY
    -0.06
     doble
    -0.06
     conducive
    -0.06
    Prés
    -0.06
     esos
    -0.06
    ﾌ
    -0.06
    POSITIVE LOGITS
    esper
    0.06
     semakin
    0.06
     часов
    0.05
    新
    0.05
     millioner
    0.05
     চিকিৎসা
    0.05
     रोक
    0.05
     our
    0.05
    there
    0.05
    哪里
    0.05
    Activations Density 0.000%

    No Known Activations