© 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. 129309
    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
     stricter
    -0.06
     страте
    -0.06
    Responsive
    -0.06
    ଗ
    -0.06
     dissatisf
    -0.05
     ارائه
    -0.05
     अभिव्य
    -0.05
    ૂ
    -0.05
     subterr
    -0.05
    responsive
    -0.05
    POSITIVE LOGITS
     lacks
    0.06
     lacked
    0.06
    additional
    0.06
     things
    0.06
    white
    0.06
     when
    0.06
     когда
    0.06
    점에서
    0.06
     ત્યારબાદ
    0.06
     adicionales
    0.06
    Activations Density 0.000%

    No Known Activations