© 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. 128538
    Prev
    Next
    INDEX
    Explanations

    mathematical and compound 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
     trio
    -0.06
     крайне
    -0.06
     averaging
    -0.06
     seien
    -0.06
     তারপর
    -0.05
    xd
    -0.05
     three
    -0.05
    ４
    -0.05
    ３
    -0.05
    अपने
    -0.05
    POSITIVE LOGITS
     معروف
    0.07
     old
    0.07
     الكهربائيه
    0.06
     correspondance
    0.06
     சூழ்
    0.06
    форми
    0.06
     anniversary
    0.06
    gesch
    0.06
    gı
    0.06
    ನು
    0.06
    Activations Density 0.001%

    No Known Activations