© 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. 117430
    Prev
    Next
    INDEX
    Explanations

    section labels

    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
     povr
    -0.07
    ㅗ
    -0.06
     delici
    -0.06
    ,
    -0.06
     மேற்பர
    -0.06
     હાલ
    -0.05
     মনোযোগ
    -0.05
     եր
    -0.05
     surrendered
    -0.05
     निम्नलिखित
    -0.05
    POSITIVE LOGITS
     these
    0.07
     этих
    0.06
     hatta
    0.06
    が無い
    0.06
     इन्हें
    0.06
     этими
    0.06
     leurs
    0.06
    Aluminum
    0.06
    这两个
    0.06
     élet
    0.06
    Activations Density 0.006%

    No Known Activations