© 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. 129602
    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
     jederzeit
    -0.07
     недавно
    -0.07
    erees
    -0.07
    很多
    -0.07
    旅游
    -0.06
     เตรียม
    -0.06
    旅遊
    -0.06
     ഇത്
    -0.06
     by
    -0.06
     最近
    -0.06
    POSITIVE LOGITS
    😜
    0.06
     illustrates
    0.06
    িলার
    0.05
     finding
    0.05
     crap
    0.05
     &,
    0.05
     willingness
    0.05
     logistics
    0.05
     find
    0.05
     idea
    0.05
    Activations Density 0.000%

    No Known Activations