© 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. 129199
    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
    ).
    -0.06
    习惯
    -0.06
    )+
    -0.06
    рои
    -0.06
     ).
    -0.05
     borehole
    -0.05
     અથ
    -0.05
    習慣
    -0.05
     பொது
    -0.05
     بہت
    -0.05
    POSITIVE LOGITS
     irmã
    0.06
    regarding
    0.06
     ელ
    0.06
    強力
    0.06
     través
    0.06
     Darüber
    0.06
     سابقا
    0.06
     şimdi
    0.06
     pidió
    0.06
     fornisce
    0.06
    Activations Density 0.000%

    No Known Activations