© 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. 120932
    Prev
    Next
    INDEX
    Explanations

    financial deficit and loss

    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
     morts
    -0.06
     www
    -0.06
     discarded
    -0.06
     effectué
    -0.06
     보통
    -0.06
     subdivided
    -0.06
     ಮಾಡಿದ್ದಾರೆ
    -0.06
    ulse
    -0.06
    低的
    -0.06
     remuneration
    -0.06
    POSITIVE LOGITS
    SWITCH
    0.06
    あなたが
    0.06
     あなた
    0.06
     لوی
    0.06
     फिजिकल
    0.06
     अर्जुन
    0.05
    Eng
    0.05
     bespoke
    0.05
     కీల
    0.05
     উভ
    0.05
    Activations Density 0.004%

    No Known Activations