© 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. 128849
    Prev
    Next
    INDEX
    Explanations

    and or combinations

    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
     your
    -0.07
     new
    -0.07
     but
    -0.07
     additional
    -0.07
     the
    -0.07
     to
    -0.06
    지만
    -0.06
     तुमच्या
    -0.06
    ;
    -0.06
    倚
    -0.06
    POSITIVE LOGITS
     आमतौर
    0.06
     বেশিরভাগ
    0.06
    નું
    0.06
    その
    0.06
    多样
    0.06
     recomendaciones
    0.06
    hawks
    0.06
     recommendations
    0.06
     ক্ষ
    0.06
    最初は
    0.06
    Activations Density 0.024%

    No Known Activations