© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 121048
    Prev
    Next
    INDEX
    Explanations

    math word problems

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     ANC
    -0.06
     the
    -0.06
     alberga
    -0.06
     zuvor
    -0.06
     कैलकु
    -0.06
    াকুর
    -0.06
    uerre
    -0.06
     bahkan
    -0.06
    émica
    -0.06
    }_{-
    -0.06
    POSITIVE LOGITS
     कर्म
    0.06
     비슷한
    0.06
     у
    0.06
     каждая
    0.06
     исход
    0.05
    inky
    0.05
    provision
    0.05
     gadgets
    0.05
     প্রশাসন
    0.05
     प्रशासन
    0.05
    Activations Density 0.006%

    No Known Activations