© 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. 120469
    Prev
    Next
    INDEX
    Explanations

    all or many words

    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
    常规
    -0.06
    新たな
    -0.06
     fascinated
    -0.06
    ходження
    -0.06
     attenzione
    -0.06
     researcher
    -0.06
     percentage
    -0.06
     adopting
    -0.06
     yüzde
    -0.06
     Percentage
    -0.06
    POSITIVE LOGITS
     semua
    0.07
     prawie
    0.06
     หลาย
    0.06
     جميع
    0.06
     also
    0.06
     بسیار
    0.06
     имеет
    0.06
     همه
    0.06
     wszyscy
    0.06
     όλ
    0.06
    Activations Density 0.001%

    No Known Activations