© 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. 120385
    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
    等を
    -0.07
     aplik
    -0.07
    dengan
    -0.07
    应用
    -0.07
     를
    -0.07
    應用
    -0.07
     setiap
    -0.07
     with
    -0.07
     dengan
    -0.07
     использовать
    -0.06
    POSITIVE LOGITS
    ászló
    0.06
     noticeable
    0.06
     even
    0.06
     deceiving
    0.06
    probably
    0.06
    ourd
    0.06
     diagnosed
    0.06
     $-$
    0.06
    largest
    0.06
     noticeably
    0.06
    Activations Density 0.000%

    No Known Activations