© 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. 120085
    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
     is
    -0.06
     Source
    -0.06
    を踏
    -0.06
     पावर
    -0.06
     viktigt
    -0.06
     metabolites
    -0.06
    結構
    -0.06
     was
    -0.06
     зас
    -0.06
     отве
    -0.05
    POSITIVE LOGITS
     brochures
    0.06
    includ
    0.06
    针对
    0.06
    ustering
    0.05
    euros
    0.05
    最新
    0.05
    但是
    0.05
     latest
    0.05
     detract
    0.05
     chores
    0.05
    Activations Density 0.000%

    No Known Activations