© 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. 117041
    Prev
    Next
    INDEX
    Explanations

    package, import, Introduction, CJ, Q

    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
    Not in Any Lists

    No Comments

    Negative Logits
    mujer
    -0.06
    Business
    -0.06
     Business
    -0.06
    ｱ
    -0.06
     solucionar
    -0.06
     incredible
    -0.06
     जब
    -0.06
     dozens
    -0.06
     পুলিশের
    -0.06
     எவ்வளவு
    -0.06
    POSITIVE LOGITS
    新しい
    0.07
     agreements
    0.06
     گیا
    0.06
     debilit
    0.06
    വസ്ഥ
    0.06
     dinding
    0.06
     parameters
    0.06
     backward
    0.06
     (=
    0.06
     agreement
    0.06
    Activations Density 0.001%

    No Known Activations