© 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. 119971
    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
    imple
    -0.06
     conferring
    -0.06
    越来越多
    -0.06
     confers
    -0.06
     cumple
    -0.06
     كلها
    -0.06
    Minimal
    -0.06
    Attention
    -0.06
    注意力
    -0.06
     energetic
    -0.06
    POSITIVE LOGITS
    baseURL
    0.07
     onus
    0.07
     outlandish
    0.06
     brainchild
    0.06
    いう
    0.06
    ঘাত
    0.06
     horrifying
    0.06
     eligible
    0.06
     thrice
    0.06
     mammoth
    0.06
    Activations Density 0.000%

    No Known Activations