© 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. 116211
    Prev
    Next
    INDEX
    Explanations

    numbers in text

    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
     không
    -0.07
     nicht
    -0.07
     não
    -0.07
     tidak
    -0.07
     සං
    -0.06
     ليس
    -0.06
     لا
    -0.06
     नहीं
    -0.06
     ikke
    -0.06
     אין
    -0.06
    POSITIVE LOGITS
     glist
    0.06
    直接
    0.06
     кусо
    0.06
    同时也
    0.06
     directly
    0.06
     भावनाओं
    0.06
    adress
    0.06
    しても
    0.06
     motivator
    0.06
     altres
    0.06
    Activations Density 0.019%

    No Known Activations