© 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. 116903
    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
    하려고
    -0.07
     не
    -0.07
    acağım
    -0.07
    を
    -0.07
    不太
    -0.07
    la
    -0.06
     line
    -0.06
     might
    -0.06
     نہیں
    -0.06
     failed
    -0.06
    POSITIVE LOGITS
     新
    0.07
     superlative
    0.07
     SPECIAL
    0.07
     nieuwe
    0.07
     前
    0.06
     上
    0.06
     avec
    0.06
    與
    0.06
     enterprising
    0.06
    Various
    0.06
    Activations Density 0.000%

    No Known Activations