© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116587
    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
    Not in Any Lists

    No Comments

    Negative Logits
    因为
    -0.07
    因為
    -0.07
     because
    -0.07
    ↵↵
    -0.07
     kerana
    -0.06
     perquè
    -0.06
    Because
    -0.06
     porque
    -0.06
     क्योंकि
    -0.06
     thậm
    -0.06
    POSITIVE LOGITS
    ೆಯೇ
    0.06
     permintaan
    0.06
     некоторых
    0.06
     sculpted
    0.06
     combinatie
    0.06
    icionados
    0.06
     constat
    0.06
     regression
    0.06
     prevalence
    0.06
     Versicherung
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.