© 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. 120541
    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
    無し
    -0.06
     굉장히
    -0.06
     didn
    -0.06
     pocas
    -0.06
     Pued
    -0.06
     rempl
    -0.06
     Miscellaneous
    -0.06
     excelente
    -0.06
    asking
    -0.06
     pocos
    -0.06
    POSITIVE LOGITS
     but
    0.07
    其中包括
    0.06
     आरंभ
    0.06
    有两种
    0.06
    😂
    0.06
    包括
    0.06
    but
    0.06
    😂😂
    0.06
     包括
    0.06
     जो
    0.06
    Activations Density 0.000%

    No Known Activations