© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129747
    Prev
    Next
    INDEX
    Explanations

    code keywords followed by declarations

    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
     على
    -0.07
     في
    -0.07
     시작
    -0.07
     प्रतिबद्ध
    -0.07
     სამ
    -0.06
     на
    -0.06
     अधिकांश
    -0.06
     البته
    -0.06
     ఇక
    -0.06
     коллеги
    -0.06
    POSITIVE LOGITS
     Which
    0.07
    There
    0.06
     there
    0.06
    which
    0.05
     There
    0.05
    there
    0.05
     said
    0.05
     which
    0.05
     öt
    0.05
     WHICH
    0.05
    Activations Density 0.002%

    No Known Activations