© 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. 115979
    Prev
    Next
    INDEX
    Explanations

    ident, Imag, Eat, Further

    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
     last
    -0.07
     उतर
    -0.07
     ઉત્પાદ
    -0.06
     internal
    -0.06
    muy
    -0.06
    Colorado
    -0.06
    Last
    -0.06
    Internal
    -0.06
    টিল
    -0.06
     कौन
    -0.06
    POSITIVE LOGITS
     mať
    0.06
     guys
    0.05
     ছিল
    0.05
    жна
    0.05
    email
    0.05
    Airport
    0.05
     cih
    0.05
     být
    0.05
     yaitu
    0.05
    John
    0.05
    Activations Density 0.001%

    No Known Activations