© 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. 116983
    Prev
    Next
    INDEX
    Explanations

    classification categories sorting

    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
    mern
    -0.06
    ponente
    -0.06
     healthful
    -0.06
     будь
    -0.06
    gear
    -0.06
    ሴ
    -0.06
     everytime
    -0.06
     той
    -0.06
    ress
    -0.06
     EDM
    -0.06
    POSITIVE LOGITS
     сорти
    0.06
     classification
    0.06
     classifications
    0.06
     classifica
    0.06
     classifying
    0.06
    subcategory
    0.06
     మొదటి
    0.06
    டுகளில்
    0.06
     categorías
    0.06
    ೆಂದು
    0.06
    Activations Density 0.004%

    No Known Activations