© 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. 119224
    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
    一个
    -0.07
    mounting
    -0.07
     pipes
    -0.06
     índ
    -0.06
     maju
    -0.06
    젝
    -0.06
     cualquier
    -0.06
     अंत
    -0.06
    icono
    -0.06
    因為
    -0.06
    POSITIVE LOGITS
     several
    0.06
     exquisite
    0.06
     বেশ
    0.06
     oft
    0.06
     the
    0.06
    lors
    0.06
     সম্পত্তি
    0.06
     несколь
    0.06
    produktion
    0.06
     supernatant
    0.05
    Activations Density 0.000%

    No Known Activations