© 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. 117033
    Prev
    Next
    INDEX
    Explanations

    mathematical solutions and queries

    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
     aquatic
    -0.07
     ‘
    -0.07
    而非
    -0.06
    水
    -0.06
     swimming
    -0.06
    游泳
    -0.06
     minus
    -0.06
    corp
    -0.06
     water
    -0.06
     आदित्यनाथ
    -0.05
    POSITIVE LOGITS
     ભારત
    0.07
    Bracketing
    0.07
     kardeş
    0.07
    OCKET
    0.07
     règles
    0.07
     Guzman
    0.06
     카드
    0.06
     الواحده
    0.06
     situazioni
    0.06
     भर
    0.06
    Activations Density 0.002%

    No Known Activations